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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and related verbs

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    örs
    -0.45
    Vanjske
    -0.44
     desaf
    -0.43
    DataSetChanged
    -0.41
    mien
    -0.40
    dynamic
    -0.40
     Laus
    -0.39
    Tower
    -0.39
     Stelle
    -0.38
     fá
    -0.37
    POSITIVE LOGITS
    ReusableCell
    0.88
    bootstrapcdn
    0.82
     дописавши
    0.74
    الحياه
    0.72
    Personensuche
    0.71
     мәкал
    0.70
    rungsseite
    0.68
     CommonModule
    0.66
    +};
    0.63
     ویکی‌پدی
    0.63
    Act Density 0.404%

    No Known Activations