Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron responds to phrasing of chemical transformations—especially redox‐type verbs like “oxidized,” “reduced,” “converted,” or “adsorbed … to.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    terms related to chemical processes and environmental remediation techniques.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _force
    -0.07
    BUS
    -0.07
     opt
    -0.07
     خطر
    -0.06
     USER
    -0.06
    .Func
    -0.06
     Stealth
    -0.06
     Div
    -0.06
    319
    -0.06
     TArray
    -0.06
    POSITIVE LOGITS
    .LatLng
    0.07
    .psi
    0.07
     которой
    0.07
    roveň
    0.07
     fost
    0.07
    .unsubscribe
    0.06
    .isVisible
    0.06
    textAlign
    0.06
    'al
    0.06
     ORIGINAL
    0.06
    Act Density 0.039%

    No Known Activations