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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values or parameters, particularly those associated with calculations or measurements

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

    3 followed by punctuation or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rinfo
    -0.58
    abank
    -0.56
    IMPORTED
    -0.56
    aving
    -0.54
     Employ
    -0.50
     lacto
    -0.50
    aip
    -0.50
    iding
    -0.49
    opo
    -0.49
     Empower
    -0.49
    POSITIVE LOGITS
    3
    0.85
     treinta
    0.56
     Constitucional
    0.56
     NoSuch
    0.55
    Kaynakça
    0.54
     Jurí
    0.54
     Suiza
    0.52
     tercera
    0.50
    NoSuch
    0.49
     terceira
    0.48
    Act Density 0.062%

    No Known Activations