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

    Neuronpedia

    INDEX
    Explanations

    direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     punitive
    -0.09
    .cash
    -0.08
     ovaj
    -0.08
    _cash
    -0.07
     گذا
    -0.07
     कट
    -0.07
    ambere
    -0.07
     switching
    -0.07
     �
    -0.07
    764
    -0.07
    POSITIVE LOGITS
     напрям
    0.10
    (Direction
    0.10
    方向
    0.09
     दिशा
    0.09
     направлении
    0.09
     направление
    0.09
     направления
    0.08
    direction
    0.08
     방향
    0.08
     orientation
    0.08
    Act Density 0.017%

    No Known Activations