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

    Neuronpedia

    INDEX
    Explanations

    public speaking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     options
    -0.07
     complaining
    -0.07
     decre
    -0.06
    #include
    -0.06
    ECTOR
    -0.06
     자세
    -0.06
    172
    -0.06
     partnering
    -0.06
     talked
    -0.06
     proposed
    -0.06
    POSITIVE LOGITS
    rna
    0.07
    _rel
    0.07
    yd
    0.06
    .responseText
    0.06
     بأ
    0.06
    ボ
    0.06
    viewer
    0.06
    _Man
    0.06
     Dag
    0.06
    恶
    0.06
    Act Density 0.082%

    No Known Activations