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

    Neuronpedia

    INDEX
    Explanations

    references to user avatars and their associated URLs

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

    avatar urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.61
    Personensuche
    -0.60
    KommentareTeilen
    -0.56
    évaluateur
    -0.54
    protoimpl
    -0.52
     CreateTagHelper
    -0.52
    ValueStyle
    -0.49
    SharedDtor
    -0.49
     maș
    -0.49
    UnknownFieldSet
    -0.49
    POSITIVE LOGITS
    vatar
    0.83
    GraphicsUnit
    0.40
     golfe
    0.39
    size
    0.34
     secure
    0.33
    hash
    0.32
    Secure
    0.32
     Secure
    0.32
     gra
    0.32
     beard
    0.31
    Act Density 0.005%

    No Known Activations