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

    Neuronpedia

    INDEX
    Explanations

    references to variations among categories

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

    different categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.83
     CreateTagHelper
    -0.63
     Photocase
    -0.60
    OCCURRED
    -0.59
    PyExc
    -0.59
    +#+#
    -0.56
     increí
    -0.55
     HasFactory
    -0.54
    </tfoot>
    -0.54
    onnaissance
    -0.53
    POSITIVE LOGITS
     sidang
    0.38
     peny
    0.38
     gegenüber
    0.37
     gewissen
    0.34
    égard
    0.33
    Usos
    0.32
     zrozum
    0.32
     bepaalde
    0.32
    thâu
    0.31
     hangi
    0.31
    Act Density 0.038%

    No Known Activations