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

    Neuronpedia

    INDEX
    Explanations

    lists and arrays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nep
    -0.08
     الدر
    -0.06
     правиль
    -0.06
     bày
    -0.06
     Pai
    -0.06
     fire
    -0.06
    ых
    -0.06
     Sek
    -0.06
    これ
    -0.06
    ียนบ
    -0.06
    POSITIVE LOGITS
    ी।
    0.07
    yclerView
    0.06
     boutique
    0.06
    	RETURN
    0.06
    ματα
    0.06
    nie
    0.06
    contenido
    0.06
     group
    0.06
    "\
    0.06
     commercials
    0.06
    Act Density 0.087%

    No Known Activations