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

    Neuronpedia

    INDEX
    Explanations

    molecular

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of a compound’s molecular weight value.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     wget
    -0.07
    刚才
    -0.07
    *X
    -0.06
    'em
    -0.06
    desktop
    -0.06
    ▍▍
    -0.06
    drawer
    -0.06
    _AES
    -0.06
    Terrain
    -0.06
     regexp
    -0.06
    POSITIVE LOGITS
     DC
    0.07
    冰
    0.07
    ippi
    0.07
    ocial
    0.07
     boca
    0.07
     Suffolk
    0.07
    atican
    0.07
    conomic
    0.06
     člověka
    0.06
    -founder
    0.06
    Act Density 0.002%

    No Known Activations