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

    Neuronpedia

    INDEX
    Explanations

    references to non-entities or non-parameters in various contexts

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

    negation prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.74
     Erwä
    -0.56
    tagHelper
    -0.54
    fjspx
    -0.53
    ingway
    -0.53
     îna
    -0.52
     HasFactory
    -0.52
     Zeitpunkt
    -0.52
     bookId
    -0.50
     courseId
    -0.50
    POSITIVE LOGITS
     non
    1.35
     Non
    1.35
    Non
    1.21
    non
    1.13
     NON
    1.08
    NON
    0.95
     nons
    0.82
     Nons
    0.82
    非
    0.81
     非
    0.75
    Act Density 0.062%

    No Known Activations