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

    Neuronpedia

    INDEX
    Explanations

    lazy loading/evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gol
    -0.07
     *,↵
    -0.07
     Charges
    -0.07
     Martha
    -0.06
    ERG
    -0.06
     Frag
    -0.06
    егодня
    -0.06
     boon
    -0.06
     PREFIX
    -0.06
    ftar
    -0.06
    POSITIVE LOGITS
    @class
    0.07
    变化
    0.06
     royalties
    0.06
    晴
    0.06
     결정
    0.06
    /int
    0.06
    icensing
    0.06
     opaque
    0.06
     upgrading
    0.06
     teleport
    0.06
    Act Density 0.010%

    No Known Activations