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

    Neuronpedia

    INDEX
    Explanations

    pandas dataframes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gpointer
    -0.08
    ;j
    -0.07
     covariance
    -0.07
    ,module
    -0.06
    spiel
    -0.06
    只不过
    -0.06
    ⨯
    -0.06
    omination
    -0.06
    不得超过
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Third
    0.08
    أسر
    0.07
    .writer
    0.07
     minced
    0.07
     mothers
    0.07
    自由贸易
    0.06
    أسواق
    0.06
     ethics
    0.06
     Women
    0.06
    HING
    0.06
    Act Density 0.015%

    No Known Activations