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

    Neuronpedia

    INDEX
    Explanations

    games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     カ
    -0.06
    ému
    -0.06
     Лі
    -0.06
     tph
    -0.06
    -го
    -0.06
    東京
    -0.06
    -names
    -0.06
     escrit
    -0.06
     nh
    -0.06
     chó
    -0.06
    POSITIVE LOGITS
    .isSuccessful
    0.07
    accumulate
    0.06
    orum
    0.06
    Reduc
    0.06
     Pew
    0.06
    sWith
    0.06
    vik
    0.06
    .yahoo
    0.06
     withholding
    0.06
    ש
    0.06
    Act Density 0.020%

    No Known Activations