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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and related auxiliary verbs.

    oai_token-act-pair · gemini-2.0-flash

    Contractions/possessives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     good
    -1.08
    good
    -1.00
    Good
    -0.81
    GOOD
    -0.77
     GOOD
    -0.75
     Good
    -0.73
     bad
    -0.71
     bueno
    -0.66
     buenos
    -0.60
    bad
    -0.59
    POSITIVE LOGITS
    apimachinery
    0.63
    日閲覧
    0.60
    الحياه
    0.60
    '])){
    0.59
     CURIAM
    0.59
    ThroughAttribute
    0.58
    owulf
    0.56
    sizeCache
    0.56
     defaultstate
    0.56
     surla
    0.54
    Act Density 1.568%

    No Known Activations