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

    Neuronpedia

    INDEX
    Explanations

    critical thinking, argumentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MetadataUsageId
    -0.07
    /dataTables
    -0.07
    .IsNotNull
    -0.07
    黥
    -0.07
     tainted
    -0.07
    cost
    -0.07
    鸮
    -0.07
    _SO
    -0.06
    Ő
    -0.06
    uesta
    -0.06
    POSITIVE LOGITS
     Korean
    0.07
    젔
    0.07
    ❃
    0.07
    _Util
    0.07
    Nearly
    0.07
    캔
    0.07
    _condition
    0.07
    ,['
    0.06
     yaşayan
    0.06
    ;base
    0.06
    Act Density 0.064%

    No Known Activations