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

    Neuronpedia

    INDEX
    Explanations

    female pronouns for possession or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    td
    0.84
    ic
    0.80
    kowe
    0.77
    p
    0.71
    鉤
    0.70
    Ich
    0.69
     Bulg
    0.66
     سلامه
    0.66
     μεγά
    0.65
    kli
    0.65
    POSITIVE LOGITS
    ли
    0.85
    ς
    0.70
    х
    0.70
    се
    0.69
    0.66
    ле
    0.66
    ز
    0.66
    <0x0D>
    0.65
    во
    0.65
    s
    0.62
    Act Density 0.004%

    No Known Activations