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

    Neuronpedia

    INDEX
    Explanations

    head

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .organization
    -0.08
    zzo
    -0.07
    }-{
    -0.07
    ,//
    -0.06
     مشتر
    -0.06
     "".
    -0.06
     interrupted
    -0.06
     substances
    -0.06
    .between
    -0.06
    OUN
    -0.06
    POSITIVE LOGITS
     wary
    0.06
     spark
    0.06
     Một
    0.06
     entr
    0.06
    multi
    0.06
     Fla
    0.06
    अ
    0.06
     Rei
    0.06
    ROWS
    0.06
    _view
    0.06
    Act Density 0.002%

    No Known Activations