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

    Neuronpedia

    INDEX
    Explanations

    phrases related to educational support and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words "papers," "assignment," or possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    articles and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.82
    findpost
    -0.78
    OGND
    -0.78
    -0.71
     تضيفلها
    -0.70
     resourceCulture
    -0.64
     AssemblyCulture
    -0.64
    WebVitals
    -0.63
     lenker
    -0.63
     Roskov
    -0.61
    POSITIVE LOGITS
     means
    0.56
     factor
    0.55
     resolution
    0.54
    ್ದ
    0.53
     quantity
    0.52
    KURZBESCHREIBUNG
    0.52
     capacity
    0.50
     selection
    0.49
     matter
    0.49
     method
    0.48
    Act Density 0.109%

    No Known Activations