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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating important locations or pivotal points within a discussion

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

    at the core

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.50
     disambiguazione
    -0.45
    Effects
    -0.45
    astéroïdes
    -0.44
    NOPQRST
    -0.44
    IntoConstraints
    -0.43
    effects
    -0.43
     ModelExpression
    -0.42
     ролях
    -0.42
     CURIAM
    -0.41
    POSITIVE LOGITS
     underlies
    0.62
     underlying
    0.60
     underlie
    0.58
     foundation
    0.57
     fundamental
    0.56
     behind
    0.55
     underpin
    0.52
     Foundation
    0.50
     central
    0.50
     basis
    0.50
    Act Density 0.112%

    No Known Activations