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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols commonly used in programming or mathematical expressions

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

    code delimiters and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Inscrivez
    -0.48
     chaude
    -0.46
     húmedo
    -0.43
    guiente
    -0.43
     fermée
    -0.40
     soudain
    -0.40
     rafraî
    -0.40
     réve
    -0.40
     Púb
    -0.39
    berdayakan
    -0.39
    POSITIVE LOGITS
    |
    1.09
    |'\
    0.96
    |()
    0.83
    |'
    0.83
    TokenNameDOT
    0.82
     |
    0.79
    |;
    0.78
    
    0.71
    |(
    0.71
    |"
    0.68
    Act Density 0.003%

    No Known Activations