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

    Neuronpedia

    INDEX
    Explanations

    instances of whitespace and newline formatting in the text

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

    code formatting and whitespace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を取り
    -0.63
    取り
    -0.63
    กระ
    -0.43
     كرة
    -0.42
    HasOne
    -0.42
     darum
    -0.35
     redonda
    -0.35
     كورة
    -0.35
     things
    -0.34
    y
    -0.33
    POSITIVE LOGITS
     bridal
    1.36
     Bridal
    1.19
    bridal
    1.08
    AutoSize
    0.69
     nowrap
    0.66
     ſch
    0.63
     protoimpl
    0.61
     myſelf
    0.60
     StringTokenizer
    0.60
    :✨
    0.59
    Act Density 0.001%

    No Known Activations