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

    Neuronpedia

    INDEX
    Explanations

    occurrences of regular expression syntax and patterns

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

    regex operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     increí
    -0.93
     indígen
    -0.88
     enfans
    -0.76
     pérd
    -0.75
    berdayakan
    -0.67
     Geiſt
    -0.67
     laſſen
    -0.67
     desmotivaciones
    -0.66
     '\\;'
    -0.66
     müſſen
    -0.66
    POSITIVE LOGITS
    zA
    0.56
    -
    0.51
     dark
    0.49
     Harry
    0.46
     Any
    0.45
    Any
    0.45
     normal
    0.44
     A
    0.43
     non
    0.42
     
    0.42
    Act Density 0.003%

    No Known Activations