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

    Neuronpedia

    INDEX
    Explanations

    patterns or sequences, possibly in a structured or coded format

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

    Tokens before hexadecimal values

    np_acts-logits-general · gemini-2.0-flash

    digits and specific characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.62
     pr
    -0.59
    iedler
    -0.57
     Ramirez
    -0.57
     the
    -0.57
     very
    -0.56
    اد
    -0.56
     Krueger
    -0.55
     Nuss
    -0.55
     a
    -0.55
    POSITIVE LOGITS
    0
    1.18
    awtextra
    1.06
    AndEndTag
    1.05
    AddTagHelper
    1.00
    vician
    0.86
     defaultstate
    0.85
    featureID
    0.85
    othed
    0.84
    ０
    0.82
     Normdatei
    0.82
    Act Density 1.101%

    No Known Activations