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

    Neuronpedia

    INDEX
    Explanations

    conversational responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PECIAL
    -0.06
    ，无
    -0.06
    partials
    -0.06
     เก
    -0.06
    executable
    -0.06
    :w
    -0.06
    _SHARED
    -0.06
    .Suppress
    -0.06
    ジュ
    -0.06
     pedido
    -0.06
    POSITIVE LOGITS
    ubah
    0.07
    __',
    0.06
     harm
    0.06
    _GUI
    0.06
     Commit
    0.06
     pivot
    0.06
    [List
    0.06
    wife
    0.06
     artwork
    0.06
     abduction
    0.06
    Act Density 0.070%

    No Known Activations