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

    Neuronpedia

    INDEX
    Explanations

    ability tooccupationsEngineers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ausea
    0.31
    avises
    0.31
     baseUrl
    0.30
     phones
    0.30
    アドレス
    0.30
    多家
    0.30
    Kaynakça
    0.30
     xAxis
    0.29
     Spann
    0.29
    ่วง
    0.29
    POSITIVE LOGITS
    alternative
    0.34
     professions
    0.33
    P
    0.32
     profession
    0.31
    now
    0.31
    occupation
    0.31
    Occupation
    0.30
    att
    0.30
    drop
    0.30
    the
    0.29
    Act Density 0.000%

    No Known Activations