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

    Neuronpedia

    INDEX
    Explanations

    Cutting tools

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     数
    -0.07
     Mongo
    -0.07
     gigs
    -0.07
    izio
    -0.06
    .lp
    -0.06
     Surv
    -0.06
    fce
    -0.06
    ndo
    -0.06
    anford
    -0.06
     SSH
    -0.06
    POSITIVE LOGITS
     hors
    0.06
    _enum
    0.06
    θερ
    0.06
     lob
    0.06
    흥
    0.06
     stopwatch
    0.06
    MIN
    0.06
     polož
    0.06
     "."
    0.05
    许多
    0.05
    Act Density 0.042%

    No Known Activations