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

    Neuronpedia

    INDEX
    Explanations

    punctuation and mathematical symbols

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

    numbers, times, and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.74
     OFDb
    -0.52
    Tembelea
    -0.49
     ExecuteAsync
    -0.47
     Мексичка
    -0.45
    Ӕ
    -0.45
     AppCompatTheme
    -0.43
    LookAnd
    -0.43
     صوتيه
    -0.43
    EndGlobalSection
    -0.42
    POSITIVE LOGITS
     nahilalakip
    0.46
     Grüsse
    0.42
    醐
    0.39
     vergeten
    0.39
     Determined
    0.38
     verzorg
    0.38
    implemented
    0.38
    centages
    0.36
    gaande
    0.36
    styleable
    0.35
    Act Density 0.310%

    No Known Activations