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

    Neuronpedia

    INDEX
    Explanations

    descriptions of simplicity and ease in processes or solutions

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

    Preceding words of "easy" or "simple"

    np_acts-logits-general · gemini-2.0-flash

    easy or simple

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.62
     indisponible
    -0.56
    aarrggbb
    -0.55
    ఔ
    -0.53
    mybatisplus
    -0.53
     ErrIntOverflow
    -0.48
    WriteBarrier
    -0.47
     AppCompatTheme
    -0.47
    สึก
    -0.46
    rsiniz
    -0.46
    POSITIVE LOGITS
     simple
    2.68
    simple
    2.48
     Simple
    2.45
    Simple
    2.38
     easy
    2.31
     SIMPLE
    2.28
     simplicity
    2.28
     simples
    2.09
     simplest
    2.05
    SIMPLE
    2.04
    Act Density 0.510%

    No Known Activations