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

    Neuronpedia

    INDEX
    Explanations

    preliminary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ethiopian
    -0.07
    zar
    -0.07
    Container
    -0.06
    .innerHeight
    -0.06
    typescript
    -0.06
     ])->
    -0.06
     hatred
    -0.06
    (UUID
    -0.06
     详情
    -0.06
    wolf
    -0.06
    POSITIVE LOGITS
     preliminary
    0.11
     Prel
    0.09
    iminary
    0.08
     determine
    0.08
     interim
    0.08
     dern
    0.07
     EM
    0.07
    ermal
    0.07
     Bulletin
    0.07
     Renew
    0.07
    Act Density 0.005%

    No Known Activations