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

    Neuronpedia

    INDEX
    Explanations

    data descriptions

    np_max-act · gemini-2.0-flash

    This neuron fires on phrases that report measured experimental data—especially numerical measurements and data‐collection details (e.g. “Body and organ weights were collected …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Err
    -0.07
    Y
    -0.07
     reclaimed
    -0.07
     rejected
    -0.06
    DDS
    -0.06
     cord
    -0.06
    ίθ
    -0.06
    ctrl
    -0.06
    HT
    -0.06
     dopamine
    -0.06
    POSITIVE LOGITS
    .ToolStrip
    0.07
    Năm
    0.07
    _core
    0.07
     MERCHANTABILITY
    0.06
     كور
    0.06
     jap
    0.06
    utschen
    0.06
    (Object
    0.06
     CharSequence
    0.06
    �
    0.06
    Act Density 0.005%

    No Known Activations