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

    Neuronpedia

    INDEX
    Explanations

    Geometry angles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frontline
    -0.08
     +=
    -0.07
     checksum
    -0.07
     oversee
    -0.07
     intoler
    -0.07
     ventricular
    -0.07
     targeted
    -0.07
     fortified
    -0.07
     marginal
    -0.07
     sizeof
    -0.07
    POSITIVE LOGITS
    Direction
    0.11
    _direction
    0.11
     dirección
    0.11
     directions
    0.10
     direction
    0.10
     दिशा
    0.10
     방향
    0.10
     clockwise
    0.10
    方向
    0.10
     outgoing
    0.10
    Act Density 0.038%

    No Known Activations