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

    Neuronpedia

    INDEX
    Explanations

    199

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /text
    -0.07
     приготовить
    -0.06
     byly
    -0.06
     mixer
    -0.06
    imin
    -0.06
     مشاهده
    -0.06
     tě
    -0.06
     grinder
    -0.06
    کل
    -0.06
     projectiles
    -0.06
    POSITIVE LOGITS
    201
    0.08
    200
    0.08
    199
    0.08
    SCREEN
    0.07
     مناس
    0.07
    .Response
    0.07
    ิด
    0.06
     Characters
    0.06
    202
    0.06
     Confidence
    0.06
    Act Density 0.002%

    No Known Activations