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

    Neuronpedia

    INDEX
    Explanations

    numerical references that indicate data or citations in a document

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

    journal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ку
    -0.33
     mon
    -0.28
     Au
    -0.24
     kul
    -0.24
     Hy
    -0.24
     salads
    -0.24
     car
    -0.24
    +:+
    -0.23
    ym
    -0.23
     z
    -0.23
    POSITIVE LOGITS
     informée
    1.00
    expandindo
    0.97
    OGND
    0.86
    niſſe
    0.85
     ddelwed
    0.84
     ब्रेकडाउन
    0.84
    GEBURTSDATUM
    0.82
     increí
    0.82
     imagui
    0.81
     estadounid
    0.81
    Act Density 0.100%

    No Known Activations