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

    Neuronpedia

    INDEX
    Explanations

    references to websites and online resources

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

    related to checking, packages, sites, and games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     keben
    -0.44
     ibunya
    -0.42
     ayudas
    -0.39
     istrinya
    -0.39
     '\\;'
    -0.38
    MigrationBuilder
    -0.38
    <bos>
    -0.38
     Juifs
    -0.38
     ljudi
    -0.37
     selaku
    -0.37
    POSITIVE LOGITS
     ſur
    0.59
     ſte
    0.57
    EndContext
    0.55
    EqualsAnd
    0.53
     GenerationType
    0.53
     EXCEL
    0.52
     unſ
    0.52
    ברס
    0.52
     smar
    0.52
    TemporalType
    0.51
    Act Density 0.012%

    No Known Activations