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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters, particularly quotes and apostrophes

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

    specific delimiters and following text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    -0.39
    ênis
    -0.36
    ts
    -0.33
    ymce
    -0.32
     time
    -0.32
    łów
    -0.32
     and
    -0.31
    is
    -0.31
    it
    -0.31
    mahaman
    -0.31
    POSITIVE LOGITS
    IUrlHelper
    0.79
    httphttps
    0.75
    __(/*!
    0.74
     @"/
    0.72
     ویکی‌پدی
    0.70
    Diweddarwch
    0.65
    mergeFrom
    0.64
    richTextPanel
    0.63
     autorytatywna
    0.63
     الحره
    0.63
    Act Density 0.004%

    No Known Activations