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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     landed
    -0.06
     algunas
    -0.06
     Surge
    -0.06
     mac
    -0.06
     yurt
    -0.06
    tur
    -0.06
     après
    -0.06
     generations
    -0.06
     algunos
    -0.06
     provinces
    -0.06
    POSITIVE LOGITS
    _inches
    0.07
    classnames
    0.07
    [Math
    0.07
     уклад
    0.07
    eliminar
    0.06
    (metric
    0.06
    skb
    0.06
    อห
    0.06
     중
    0.06
    ,{↵
    0.06
    Act Density 0.011%

    No Known Activations