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

    Neuronpedia

    INDEX
    Explanations

    references to specific measurements or parameters within technical contexts

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

    introduces clauses or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.66
     فريبيس
    -0.59
    ConstraintMaker
    -0.57
    addPreferredGap
    -0.57
    WriteTagHelper
    -0.56
     Taktlose
    -0.55
     Signalez
    -0.54
     Exactos
    -0.54
    Tembelea
    -0.50
    ьаж
    -0.49
    POSITIVE LOGITS
     faltan
    0.43
     podmín
    0.40
     sonunda
    0.40
    Espero
    0.39
     Erfahrung
    0.39
     Erfahrungen
    0.39
     Hoffnung
    0.38
     infeliz
    0.38
     Neither
    0.37
     speranza
    0.37
    Act Density 0.025%

    No Known Activations