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
     ViewState
    -0.07
    .jface
    -0.07
    iếu
    -0.06
    _CD
    -0.06
    ีโอ
    -0.06
     Preis
    -0.06
     Decrypt
    -0.06
     напрям
    -0.06
    siyon
    -0.06
     God
    -0.06
    POSITIVE LOGITS
    ）↵
    0.07
     전세가
    0.07
     لكل
    0.06
    :%
    0.06
    verages
    0.06
     mais
    0.06
    asma
    0.06
    ักก
    0.06
     "../../../
    0.06
    駐
    0.06
    Act Density 0.011%

    No Known Activations