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

    Neuronpedia

    INDEX
    Explanations

    cake and feminine wear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $
    0.62
    '
    0.57
     bertahan
    0.53
     yac
    0.50
    ה
    0.49
     drugi
    0.47
    т
    0.47
     on
    0.47
    :
    0.47
     å
    0.46
    POSITIVE LOGITS
    in
    0.82
     ワンピース
    0.72
     princesses
    0.69
    👸
    0.67
     váy
    0.64
    👠
    0.64
     केक
    0.63
     WTA
    0.63
     actresses
    0.63
     بنات
    0.63
    Act Density 0.297%

    No Known Activations