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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     지난
    -0.07
    cj
    -0.07
    prung
    -0.07
    *((
    -0.07
    �
    -0.06
    为什么
    -0.06
    jud
    -0.06
    ━�
    -0.06
     cj
    -0.06
    '",↵
    -0.06
    POSITIVE LOGITS
     AES
    0.07
     Beard
    0.07
    fts
    0.07
     deals
    0.07
    A
    0.07
    fulness
    0.06
    232
    0.06
    не
    0.06
    _plus
    0.06
     restriction
    0.06
    Act Density 0.000%

    No Known Activations