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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or items within a context

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

    sequences of numbers and letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoreMessageInfo
    -0.52
    出版年
    -0.48
     cristianismo
    -0.44
    TagMode
    -0.43
    bootstrapcdn
    -0.42
    PhysRevD
    -0.40
    RectangleBorder
    -0.39
     wikipagina
    -0.39
     kennis
    -0.38
    Tikang
    -0.38
    POSITIVE LOGITS
    tonode
    0.54
     مشين
    0.54
    OrNil
    0.49
    יסטור
    0.48
     Plu
    0.47
     Wor
    0.47
    хьтан
    0.46
    Writable
    0.46
     Competence
    0.45
    makeText
    0.45
    Act Density 0.100%

    No Known Activations