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

    Neuronpedia

    INDEX
    Explanations

    slavic names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AUDIO
    -0.08
     пять
    -0.07
    (assign
    -0.07
    [p
    -0.07
    _dt
    -0.07
    -my
    -0.06
    (',
    -0.06
     anunci
    -0.06
     koje
    -0.06
     относится
    -0.06
    POSITIVE LOGITS
    visor
    0.07
    탕
    0.07
     literacy
    0.07
    녁
    0.06
    olini
    0.06
     阿
    0.06
     Phys
    0.06
     те
    0.06
    rel
    0.06
    рок
    0.06
    Act Density 0.008%

    No Known Activations