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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific structural or formatting elements, such as sections and lists, in the document

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

    Punctuation after questions or quotes

    np_acts-logits-general · gemini-2.0-flash

    conditional statements and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumii
    -0.57
     nė
    -0.55
     Simplemente
    -0.54
    simply
    -0.52
     Ironically
    -0.52
    Quite
    -0.51
     дописавши
    -0.51
     initially
    -0.51
     simply
    -0.49
     Incluso
    -0.48
    POSITIVE LOGITS
     XYZ
    1.16
     blah
    1.14
    〇〇
    0.99
     X
    0.99
    !”.
    0.98
     xyz
    0.97
    !”,
    0.93
    ○○
    0.91
     ____
    0.89
    XYZ
    0.86
    Act Density 0.241%

    No Known Activations