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

    Neuronpedia

    INDEX
    Explanations

    special formatting elements or symbols in text

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

    evaluation and asked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Географиясе
    -0.59
     متعلقه
    -0.57
     ModelExpression
    -0.56
    Autoritní
    -0.56
    InjectAttribute
    -0.55
     ſou
    -0.54
     queſta
    -0.52
     CommandType
    -0.52
     ſind
    -0.51
    Bibliograf
    -0.51
    POSITIVE LOGITS
    ScopeManager
    0.29
    はじめに
    0.28
    LookAnd
    0.28
    AddTagHelper
    0.28
     cra
    0.26
     pokok
    0.26
    เด
    0.26
     Jungs
    0.26
     banderas
    0.26
    ruik
    0.25
    Act Density 0.152%

    No Known Activations