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

    Neuronpedia

    INDEX
    Explanations

    technical terms and programming-related language patterns

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

    Mathematical expressions with exponents

    np_acts-logits-general · gemini-2.0-flash

    foam roller devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.54
    transQ
    -0.54
     otomatig
    -0.52
    ########.
    -0.48
     bēr
    -0.45
    RTEX
    -0.43
     fashiola
    -0.43
     Coffin
    -0.43
    fromnode
    -0.43
     clearColor
    -0.43
    POSITIVE LOGITS
    تقاوى
    0.45
    новниш
    0.40
    dafx
    0.39
     незавершена
    0.39
    stateParams
    0.38
     nakalista
    0.38
     GenerationType
    0.38
    izr
    0.37
     DbSet
    0.34
    Спасылкі
    0.33
    Act Density 1.163%

    No Known Activations