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

    Neuronpedia

    INDEX
    Explanations

    Version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     untuk
    -0.07
     inflict
    -0.07
    Surv
    -0.07
     Certif
    -0.07
     contingent
    -0.07
     samen
    -0.07
    .loaded
    -0.07
     ruins
    -0.06
     butt
    -0.06
    r
    -0.06
    POSITIVE LOGITS
     goalie
    0.07
    {/*
    0.07
    .we
    0.06
    /types
    0.06
    ”.↵
    0.06
     erot
    0.06
    pi
    0.06
    OKIE
    0.06
    Lin
    0.06
     애
    0.06
    Act Density 0.001%

    No Known Activations