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

    Neuronpedia

    INDEX
    Explanations

    Text reading direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ప్రమాద
    -0.08
    업
    -0.07
     bapt
    -0.07
     tasked
    -0.07
     امکانات
    -0.07
     risking
    -0.07
    gence
    -0.07
    069
    -0.07
     berat
    -0.07
    hecimento
    -0.07
    POSITIVE LOGITS
     Reihen
    0.14
    Direction
    0.14
    順
    0.14
    _direction
    0.13
    _DIRECTION
    0.13
    (reverse
    0.13
     direction
    0.13
    _reverse
    0.13
     clockwise
    0.13
    (Direction
    0.13
    Act Density 0.017%

    No Known Activations