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

    Neuronpedia

    INDEX
    Explanations

    references to programming terms and libraries

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

    programming languages and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ke
    -0.45
    ed
    -0.42
     ta
    -0.41
     my
    -0.40
    my
    -0.39
    sp
    -0.39
    uatu
    -0.37
     pick
    -0.37
    es
    -0.36
     speciali
    -0.36
    POSITIVE LOGITS
     Autorizaciones
    0.56
     незавершена
    0.52
    posedge
    0.51
     snippetHide
    0.50
     متعلقه
    0.50
    بوابة
    0.48
     autorytatywna
    0.48
     ब्रेकडाउन
    0.48
     CURIAM
    0.47
    Diweddarwch
    0.47
    Act Density 0.045%

    No Known Activations