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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '_
    -0.07
     являются
    -0.07
    -Line
    -0.07
    baru
    -0.07
    ulf
    -0.07
    720
    -0.06
    legen
    -0.06
     lineHeight
    -0.06
    -circle
    -0.06
     lyric
    -0.06
    POSITIVE LOGITS
    (document
    0.07
     rockets
    0.07
    _rx
    0.06
    .play
    0.06
     кг
    0.06
     PLATFORM
    0.06
     oi
    0.06
    .reject
    0.06
    μα
    0.06
     till
    0.06
    Act Density 0.048%

    No Known Activations