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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بخش
    -0.07
    _Se
    -0.06
    _BT
    -0.06
    Analy
    -0.06
    Это
    -0.06
    (am
    -0.06
     програм
    -0.06
     sexdate
    -0.06
    fce
    -0.06
     verifying
    -0.06
    POSITIVE LOGITS
     regenerate
    0.07
     salv
    0.07
     hip
    0.07
     pozisyon
    0.07
    ulling
    0.06
    aget
    0.06
    vern
    0.06
     поп
    0.06
    646
    0.06
    なが
    0.06
    Act Density 0.001%

    No Known Activations