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

    Neuronpedia

    INDEX
    Explanations

    .php

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abilities
    -0.07
    力を
    -0.07
    ildi
    -0.07
    icers
    -0.06
     모두
    -0.06
     exem
    -0.06
    .fit
    -0.06
    онов
    -0.06
    *>
    -0.06
     Bundes
    -0.06
    POSITIVE LOGITS
     структур
    0.07
     pixels
    0.06
    claims
    0.06
     characterized
    0.06
     crippling
    0.06
    /+
    0.06
    ylum
    0.06
     futures
    0.06
    ,P
    0.06
     vibrating
    0.06
    Act Density 0.008%

    No Known Activations