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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulae

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gray
    -0.08
    位置
    -0.07
     gee
    -0.07
    EATURE
    -0.07
    .sourceforge
    -0.07
     Coy
    -0.07
    resident
    -0.07
     gri
    -0.07
    햋
    -0.07
    一部分
    -0.07
    POSITIVE LOGITS
    :numel
    0.08
     delights
    0.07
     sond
    0.07
     Marilyn
    0.07
    SHARE
    0.07
    �
    0.07
    ([{
    0.07
     SUM
    0.06
    圣经
    0.06
     INPUT
    0.06
    Act Density 0.003%

    No Known Activations