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

    Neuronpedia

    INDEX
    Explanations

    informal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snake
    -0.07
    ?:
    -0.07
    /master
    -0.07
     spins
    -0.07
    rolling
    -0.06
     calculates
    -0.06
     덤프
    -0.06
     pellet
    -0.06
     frozen
    -0.06
     princ
    -0.06
    POSITIVE LOGITS
     Lieutenant
    0.07
     Vict
    0.07
     лиц
    0.06
    WSC
    0.06
     ImageIcon
    0.06
    พน
    0.06
    .ImageIcon
    0.06
     Advice
    0.06
    malar
    0.06
     numéro
    0.06
    Act Density 0.087%

    No Known Activations