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

    Neuronpedia

    INDEX
    Explanations

    him, his, her pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    profitable
    0.60
    ható
    0.59
     اصول
    0.59
    juan
    0.58
    zada
    0.57
    andad
    0.56
    ゾート
    0.56
    czak
    0.55
    matplotlib
    0.55
    FFECT
    0.55
    POSITIVE LOGITS
     him
    1.67
    him
    1.30
     his
    1.29
     ему
    1.18
     его
    1.14
     lui
    1.13
    彼の
    1.08
     her
    1.06
    他的
    1.03
     нему
    1.03
    Act Density 0.000%

    No Known Activations