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

    Neuronpedia

    INDEX
    Explanations

    construction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decorating
    -0.07
    halt
    -0.07
    ptr
    -0.06
    _lo
    -0.06
     Karel
    -0.06
    Tower
    -0.06
    plevel
    -0.06
     Cowboy
    -0.06
     really
    -0.06
    ět
    -0.06
    POSITIVE LOGITS
    _PUR
    0.06
    ellipse
    0.06
     longitudinal
    0.06
    :return
    0.06
     oxidative
    0.06
     soared
    0.06
    FileSystem
    0.06
     windowHeight
    0.06
     soaring
    0.06
     захворю
    0.06
    Act Density 0.018%

    No Known Activations