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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BE
    -0.07
    .rm
    -0.07
    DP
    -0.07
    이
    -0.07
    wap
    -0.07
    .Orders
    -0.06
    .MaxValue
    -0.06
     гір
    -0.06
     Israeli
    -0.06
    EVER
    -0.06
    POSITIVE LOGITS
     translator
    0.06
     roční
    0.06
     Sag
    0.06
    LoadIdentity
    0.06
     works
    0.06
    :::::|
    0.06
    AppState
    0.06
    нул
    0.05
     улы
    0.05
    effect
    0.05
    Act Density 0.020%

    No Known Activations