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

    Neuronpedia

    INDEX
    Explanations

    advanced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Owl
    -0.07
    Од
    -0.07
    도의
    -0.06
     Columbia
    -0.06
    deps
    -0.06
    她
    -0.06
    _INIT
    -0.06
     мног
    -0.06
    _stats
    -0.06
     widened
    -0.06
    POSITIVE LOGITS
    -aos
    0.06
    омет
    0.06
    ?>>
    0.06
    etsy
    0.06
    .Ultra
    0.06
    絵
    0.06
    aoke
    0.06
    /story
    0.06
     suis
    0.06
     Natal
    0.06
    Act Density 0.022%

    No Known Activations