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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ACK
    -0.06
     }),
    -0.06
    孩子
    -0.06
    _EDGE
    -0.06
    LEN
    -0.06
    .To
    -0.06
    _trace
    -0.06
     pasta
    -0.06
    apon
    -0.06
    asant
    -0.06
    POSITIVE LOGITS
    says
    0.07
    /dir
    0.06
    �
    0.06
     ピ
    0.06
     tekn
    0.06
    (coeff
    0.06
     finde
    0.06
    _perms
    0.06
     Y
    0.06
    Rated
    0.06
    Act Density 0.009%

    No Known Activations