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

    Neuronpedia

    INDEX
    Explanations

    books

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buddy
    -0.06
    ーダ
    -0.06
     TXT
    -0.06
    _DELTA
    -0.06
    enia
    -0.06
     Fourier
    -0.06
     prostřed
    -0.06
    уска
    -0.06
    /profile
    -0.06
     breeds
    -0.06
    POSITIVE LOGITS
    pies
    0.06
     Nhất
    0.06
    (hand
    0.06
     navig
    0.06
    ào
    0.06
    -stats
    0.06
     tep
    0.05
    battle
    0.05
    طلب
    0.05
     hội
    0.05
    Act Density 0.020%

    No Known Activations