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

    Neuronpedia

    INDEX
    Explanations

    social identity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tonnes
    -0.09
     מקצוע
    -0.08
     사업
    -0.08
     ингреди
    -0.08
     овощ
    -0.08
     лекарства
    -0.08
     Philosophy
    -0.08
     statutory
    -0.08
     самые
    -0.08
    pgsql
    -0.08
    POSITIVE LOGITS
    群
    0.11
    -group
    0.10
     interpersonal
    0.10
    成员
    0.10
    leader
    0.10
     membership
    0.10
    Leader
    0.09
     conformity
    0.09
    /group
    0.09
     leader
    0.09
    Act Density 0.012%

    No Known Activations