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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical operations and set theory concepts

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

    exclusion principle, not (), removing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Erle
    -0.46
    virons
    -0.44
    AndEndTag
    -0.42
    thora
    -0.42
     Majefty
    -0.41
    endphp
    -0.41
    setVerticalGroup
    -0.41
    wester
    -0.40
    iconic
    -0.40
    magem
    -0.40
    POSITIVE LOGITS
    ModelAdmin
    0.58
    хьтан
    0.47
    Personensuche
    0.47
    ThroughAttribute
    0.46
     مشين
    0.46
    hoeddwyd
    0.46
     שוליים
    0.45
    @[+][
    0.43
    LookAnd
    0.43
     exclusions
    0.42
    Act Density 0.163%

    No Known Activations