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

    Neuronpedia

    INDEX
    Explanations

    pointers or references used in programming languages

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

    citations with volume numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.67
    ist
    -0.48
    ~
    -0.46
    M
    -0.41
    :
    -0.40
    -
    -0.38
     maquin
    -0.36
    »
    -0.36
    chargez
    -0.36
    namiento
    -0.35
    POSITIVE LOGITS
     **
    1.02
     يتيمه
    0.82
     للمعارف
    0.77
     ſehr
    0.75
    BibitemShut
    0.75
     ‘‘
    0.74
     ſind
    0.73
    iſen
    0.69
     Normdatei
    0.69
    ſelben
    0.68
    Act Density 0.055%

    No Known Activations