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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SSH
    -0.07
    سية
    -0.07
    _Data
    -0.07
    -chain
    -0.07
     Razor
    -0.07
    DataType
    -0.06
    perl
    -0.06
    SID
    -0.06
    mu
    -0.06
     kesin
    -0.06
    POSITIVE LOGITS
    宫
    0.06
    사의
    0.06
    ỏ
    0.06
     również
    0.06
    .....
    0.06
     ضد
    0.06
     financially
    0.06
     proximity
    0.06
     disgusting
    0.06
    ;


↵
    0.06
    Act Density 0.000%

    No Known Activations