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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쉼
    -0.07
     Marr
    -0.07
    Fuse
    -0.07
    试验
    -0.07
    蕺
    -0.07
    刈
    -0.07
    дей
    -0.06
    Repair
    -0.06
    _heads
    -0.06
    amina
    -0.06
    POSITIVE LOGITS
     серьезн
    0.07
     dependent
    0.07
     slicing
    0.07
    witter
    0.07
    -ed
    0.07
     포함
    0.07
    inherit
    0.07
     recommendation
    0.06
    -placeholder
    0.06
     כלומר
    0.06
    Act Density 0.002%

    No Known Activations