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

    Neuronpedia

    INDEX
    Explanations

    interactions and responses related to understanding, support, and choice-making in various contexts

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

    help and decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteAttribute
    -0.49
     surla
    -0.46
     فريبيس
    -0.45
     whistle
    -0.43
    RegistryLite
    -0.42
     Pende
    -0.41
    ConstraintMaker
    -0.40
     whist
    -0.40
    typeorm
    -0.39
     Whistle
    -0.39
    POSITIVE LOGITS
    queles
    0.48
     zijne
    0.46
    ţei
    0.45
     Anschließend
    0.44
     těch
    0.44
    disfraz
    0.44
     mijne
    0.44
     OMITBAD
    0.44
     argint
    0.44
     też
    0.43
    Act Density 0.034%

    No Known Activations