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

    Neuronpedia

    INDEX
    Explanations

    numerical values or references to coding scripts

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

    months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createState
    -0.63
     createSprite
    -0.45
     вікісторінку
    -0.44
     Anfitrión
    -0.43
     Milán
    -0.43
     Turquía
    -0.41
     Dinamarca
    -0.39
     Comprometido
    -0.38
     Egipto
    -0.36
     například
    -0.36
    POSITIVE LOGITS
     June
    0.65
     November
    0.63
     December
    0.62
    sidemargin
    0.62
     February
    0.62
     August
    0.60
     July
    0.59
     March
    0.59
     September
    0.59
     October
    0.58
    Act Density 0.012%

    No Known Activations