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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically parentheses and braces

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

    user input prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ::~
    -0.51
    󠁮
    -0.49
    EndInit
    -0.48
     kasarigan
    -0.46
     *__
    -0.45
     noqa
    -0.45
    |};
    -0.44
    //~
    -0.44
    Бахар
    -0.44
     []*
    -0.43
    POSITIVE LOGITS
    (
    0.74
     poichè
    0.52
     (
    0.49
     whoſe
    0.47
    >(
    0.47
     telefónica
    0.45
     húmedo
    0.44
     anledning
    0.44
     quæ
    0.43
    >(</
    0.43
    Act Density 0.000%

    No Known Activations