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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "and" along with surrounding words

    oai_token-act-pair · gemini-2.0-flash

    words with unique characters or variations

    np_token-act-pair-logits · gpt-4o-mini

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enumi
    -1.00
    enumii
    -0.90
    UserScript
    -0.86
    +#+#
    -0.77
     nakalista
    -0.74
    NameInMap
    -0.74
     /\.
    -0.74
     Italijanski
    -0.72
    <bos>
    -0.71
    bootstrapcdn
    -0.70
    POSITIVE LOGITS
     مواليد
    0.59
     tartalomajánló
    0.58
     myſelf
    0.57
     becauſe
    0.57
     againſt
    0.57
     Theſe
    0.55
     itſelf
    0.54
     Româ
    0.54
     whoſe
    0.53
     poffible
    0.53
    Act Density 1.891%

    No Known Activations