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

    Neuronpedia

    INDEX
    Explanations

    direct quotations or reported speech in the text

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

    reporting verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.53
     ModelExpression
    -0.49
    Ծանոթ
    -0.47
     actionMode
    -0.46
     esterni
    -0.46
    Kjelder
    -0.45
     مرئيه
    -0.45
     出版
    -0.44
     Geſch
    -0.44
    зулта
    -0.43
    POSITIVE LOGITS
     typelib
    0.49
     насељу
    0.40
    KommentareTeilen
    0.39
     sillä
    0.37
     Италијани
    0.37
     Rays
    0.35
     ब्रेकडाउन
    0.35
    ahead
    0.34
     ANNOUNC
    0.34
     solides
    0.34
    Act Density 0.039%

    No Known Activations