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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    倾向
    -0.07
    してください
    -0.07
    =w
    -0.07
    ﾏ
    -0.07
     )
↵
↵
    -0.06
     divergence
    -0.06
    arking
    -0.06
    ่ะ
    -0.06
    visit
    -0.06
     burden
    -0.06
    POSITIVE LOGITS
     Poll
    0.07
    _EVAL
    0.07
     aj
    0.07
     Sessions
    0.07
    -switch
    0.07
    _vectors
    0.07
     fiscal
    0.06
     giveaways
    0.06
    Statistics
    0.06
     sig
    0.06
    Act Density 0.037%

    No Known Activations