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

    Neuronpedia

    INDEX
    Explanations

    instructions, prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Saga
    -0.07
     saldırı
    -0.07
     medial
    -0.07
     güven
    -0.07
     cią
    -0.07
    IFDEF
    -0.07
    靥
    -0.07
     Insert
    -0.07
     Greenland
    -0.07
    אוגוס
    -0.06
    POSITIVE LOGITS
    ouncements
    0.09
    ework
    0.07
    냈
    0.07
     exporters
    0.07
     financier
    0.07
    التز
    0.07
     Each
    0.07
    >*
    0.07
     Раз
    0.07
    lt
    0.07
    Act Density 0.003%

    No Known Activations