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

    Neuronpedia

    INDEX
    Explanations

    specific statistical data or results within research articles, particularly in the context of scientific studies or trials

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

    Numbers in square brackets

    np_acts-logits-general · gemini-2.0-flash

    numbers after citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enti
    -0.46
     nine
    -0.43
     patrón
    -0.43
    цепт
    -0.43
    Eight
    -0.41
    SEVEN
    -0.41
    Seven
    -0.41
    ानी
    -0.41
    azan
    -0.41
    LEncoder
    -0.41
    POSITIVE LOGITS
    CloseOperation
    0.82
     hundred
    0.79
     hundreds
    0.76
    hundreds
    0.72
    EDEFAULT
    0.72
    hundred
    0.70
    ">:
    0.66
     Hundreds
    0.63
     ratusan
    0.61
     HUND
    0.61
    Act Density 0.366%

    No Known Activations