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

    Neuronpedia

    INDEX
    Explanations

    \t

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jain
    -0.07
    oble
    -0.07
    Setup
    -0.07
    warnings
    -0.07
     boon
    -0.07
    roc
    -0.07
     I
    -0.07
     Venus
    -0.07
     TY
    -0.06
     reputable
    -0.06
    POSITIVE LOGITS
     appet
    0.07
     литератур
    0.07
    쭙
    0.06
    ель
    0.06
    [left
    0.06
    슛
    0.06
    꾜
    0.06
    퍼
    0.06
    certificate
    0.06
    ód
    0.06
    Act Density 0.002%

    No Known Activations