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

    Neuronpedia

    INDEX
    Explanations

    punctuation and structural elements in written text

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

    Text before and after conditional statements

    np_acts-logits-general · gemini-2.0-flash

    contrast or condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.86
    IsMutable
    -0.80
     '\\;'
    -0.71
    Personensuche
    -0.69
     contextLoads
    -0.68
     كومونز
    -0.67
    bootstrapcdn
    -0.66
     AppColors
    -0.65
     ModelExpression
    -0.65
    __':
    -0.64
    POSITIVE LOGITS
     Conversely
    0.81
     conversely
    0.75
     sebaliknya
    0.72
    Conversely
    0.66
     vice
    0.61
     Otherwise
    0.56
     if
    0.54
     vise
    0.53
     otherwise
    0.51
    RegressionTest
    0.51
    Act Density 0.480%

    No Known Activations