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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that signal the end of a sentence

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

    Code, math, or special characters

    np_acts-logits-general · gemini-2.0-flash

    code delimiters and variable declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rhestr
    -0.69
     محفوظة
    -0.68
     EClass
    -0.65
    </tfoot>
    -0.64
     \$
    -0.63
     незавершена
    -0.61
     torchvision
    -0.61
     :\\
    -0.60
     تضيفلها
    -0.59
     tartalomajánló
    -0.58
    POSITIVE LOGITS
    <em>
    1.85
    <i>
    1.72
    <code>
    0.88
     /*
    0.79
    /*
    0.78
     
    0.75
    《
    0.69
     《
    0.66
     $
    0.64
    『
    0.62
    Act Density 0.055%

    No Known Activations