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

    Neuronpedia

    INDEX
    Explanations

    pounds and deposits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ทั้ง
    0.80
    [^
    0.79
     Đ
    0.79
     Só
    0.78
     vàng
    0.77
    ಜ್ಞ
    0.76
    िं
    0.76
     Änderung
    0.76
     좌표
    0.75
    جنة
    0.74
    POSITIVE LOGITS
    uevo
    0.78
    ltre
    0.76
    iche
    0.75
     suing
    0.73
    you
    0.72
    ́s
    0.71
    tf
    0.71
    TF
    0.71
    гова
    0.70
     trae
    0.70
    Act Density 0.003%

    No Known Activations