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

    Neuronpedia

    INDEX
    Explanations

    punctuation and mathematical symbols in the text

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

    sequences containing numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Beren
    -0.48
    لیسی
    -0.44
     Umar
    -0.42
     McKee
    -0.42
    SerializedSize
    -0.42
    empereur
    -0.41
     فريبيس
    -0.41
    UserDto
    -0.41
     Melvin
    -0.41
    seende
    -0.41
    POSITIVE LOGITS
     forties
    0.53
     Forty
    0.52
    AndroidJUnit
    0.51
     forty
    0.50
    Forty
    0.46
     currentState
    0.45
     quarante
    0.45
    forty
    0.45
     onOptions
    0.44
     Fifty
    0.42
    Act Density 0.298%

    No Known Activations