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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scandals and criticisms of organizations or governments

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

    adverbs followed by prepositions or nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.54
     виправивши
    -0.47
    InOrder
    -0.46
    expandindo
    -0.45
     royals
    -0.45
    IsMutable
    -0.42
    Bits
    -0.41
    Portale
    -0.41
    NSData
    -0.41
    bolista
    -0.40
    POSITIVE LOGITS
    FunctionFlags
    0.53
    pantalones
    0.48
     defaultstate
    0.45
    новништво
    0.43
     caused
    0.42
    efficacité
    0.41
    classnames
    0.41
    exécution
    0.40
     causing
    0.38
    !*\
    0.38
    Act Density 0.010%

    No Known Activations