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

    Neuronpedia

    INDEX
    Explanations

    assertions and statements of fact

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

    Contractions with "is"

    np_acts-logits-general · gemini-2.0-flash

    judging qualities and difficulties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.64
     resourceCulture
    -0.63
    :✨
    -0.63
     jLabel
    -0.63
    IUrlHelper
    -0.62
     rire
    -0.57
     privées
    -0.57
     Constellation
    -0.56
     rayures
    -0.56
     scolaires
    -0.55
    POSITIVE LOGITS
     hard
    0.57
     nice
    0.55
     kind
    0.54
    міністра
    0.52
     such
    0.50
     difficult
    0.50
     tricky
    0.49
    UVEN
    0.49
    RectangleBorder
    0.49
     sort
    0.48
    Act Density 0.137%

    No Known Activations