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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    说明书
    -0.08
    istrator
    -0.07
     candidates
    -0.07
    iter
    -0.07
    ไข
    -0.07
    image
    -0.07
     Matrix
    -0.07
    🅖
    -0.06
    댘
    -0.06
    .value
    -0.06
    POSITIVE LOGITS
    回购
    0.09
     //////////////////////////////////////////////////////////////////////
    0.08
    嬖
    0.07
    ((&
    0.07
    Svc
    0.07
     alışver
    0.07
    选�
    0.07
    [first
    0.07
     intimidation
    0.07
     repos
    0.07
    Act Density 0.014%

    No Known Activations