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

    Neuronpedia

    INDEX
    Explanations

    affirm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sanct
    -0.07
     Knicks
    -0.07
    perc
    -0.06
    盈利
    -0.06
    ﰐ
    -0.06
     publicKey
    -0.06
     hoax
    -0.06
     طفل
    -0.06
     Bind
    -0.06
    ा
    -0.06
    POSITIVE LOGITS
     []
    0.07
    sites
    0.07
    出差
    0.07
    ikhail
    0.07
    .tracks
    0.07
    红豆
    0.06
    [:]
    0.06
    プロジェクト
    0.06
    dots
    0.06
    材料
    0.06
    Act Density 0.001%

    No Known Activations