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

    Neuronpedia

    INDEX
    Explanations

    non-zero numerical values associated with statistical or quantitative information

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

    large numbers with commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мәкал
    -0.51
     Мексичка
    -0.48
    :✨
    -0.48
     destacados
    -0.46
    <bos>
    -0.46
     Schmid
    -0.45
     мәкалә
    -0.45
     …
    -0.42
    Рисунок
    -0.42
     profundos
    -0.42
    POSITIVE LOGITS
    0
    0.84
    <?,
    0.51
    ０
    0.44
    DataAnnotations
    0.44
    PointerException
    0.43
    AutoScaleMode
    0.43
    []
    0.42
     Epoch
    0.42
    RTEX
    0.41
    InteropServices
    0.41
    Act Density 0.016%

    No Known Activations