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

    Neuronpedia

    INDEX
    Explanations

    code delimiters or prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    readlines
    -0.90
     ceinture
    -0.79
     breathable
    -0.79
    関係
    -0.78
    writeField
    -0.75
    тиза
    -0.75
    Élet
    -0.75
    provoking
    -0.75
    šte
    -0.74
     Waugh
    -0.73
    POSITIVE LOGITS
     alts
    0.87
     실패
    0.87
     choice
    0.85
     sequence
    0.85
     failure
    0.85
     Choice
    0.84
     Epson
    0.82
     failures
    0.82
     succeeds
    0.80
     Matches
    0.79
    Act Density 0.029%

    No Known Activations