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

    Neuronpedia

    INDEX
    Explanations

    percentage signs and numerical values

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

    Percent signs followed by specific characters

    np_acts-logits-general · gemini-2.0-flash

    format specifiers and placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yargs
    -0.80
    __*/
    -0.71
    DeleteBehavior
    -0.71
     nahilalakip
    -0.65
    ngths
    -0.65
     Administrativna
    -0.64
     doInBackground
    -0.63
    umą
    -0.62
    வு
    -0.61
    principalTable
    -0.61
    POSITIVE LOGITS
    ="%
    0.94
    ='%
    0.93
    :%
    0.87
    /%
    0.86
    -%
    0.85
    ('%
    0.84
    _%
    0.83
    }%
    0.83
    =%
    0.82
    ("%
    0.81
    Act Density 0.249%

    No Known Activations