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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     occured
    -0.06
     '>'
    -0.06
    [Int
    -0.06
    _BYTE
    -0.06
     snake
    -0.06
     {?
    -0.06
    cnt
    -0.06
     tox
    -0.06
    cntl
    -0.06
    Far
    -0.06
    POSITIVE LOGITS
    вищ
    0.07
    رفت
    0.07
    ış
    0.07
    ñana
    0.07
     insists
    0.06
    她们
    0.06
     pohled
    0.06
    season
    0.06
    (firstName
    0.06
    suspend
    0.06
    Act Density 0.001%

    No Known Activations