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

    Neuronpedia

    INDEX
    Explanations

    instances of textual delimiters or punctuation in the document

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

    References or citations

    np_acts-logits-general · gemini-2.0-flash

    citation numbers and brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gradova
    -0.59
    $_['
    -0.55
    andExpect
    -0.55
    antMatchers
    -0.53
    basicConfig
    -0.51
    BorderFactory
    -0.50
     iprot
    -0.49
    /*++
    -0.49
    PreAuthorize
    -0.49
    asList
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.74
    IUrlHelper
    0.67
    SourceChecksum
    0.65
    دانشنامهٔ
    0.64
     cherchés
    0.61
    featureID
    0.58
    MLLoader
    0.58
     الاطلاع
    0.57
     Fakta
    0.54
    ThroughAttribute
    0.54
    Act Density 0.043%

    No Known Activations