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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal concern and uncertainty

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

    Follows single characters or short strings

    np_acts-logits-general · gemini-2.0-flash

    swear words, expletives, and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -1.02
    NameInMap
    -0.92
    <bos>
    -0.91
    `;
    -0.89
    '},
    -0.88
    >`;
    -0.88
     كومونز
    -0.85
    GenerationType
    -0.85
     */
    -0.84
    [])
    -0.83
    POSITIVE LOGITS
    .
    1.07
     fucking
    0.89
    ,
    0.86
    !
    0.83
    …
    0.79
     freakin
    0.76
     fuckin
    0.73
     FUCKING
    0.69
     stuff
    0.67
    ….
    0.66
    Act Density 0.534%

    No Known Activations