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

    Neuronpedia

    INDEX
    Explanations

    movement and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вій
    0.37
    レア
    0.34
     सारे
    0.33
     যথাযথ
    0.32
     terbesar
    0.32
     संध्या
    0.32
    뎃
    0.32
     ഓ
    0.32
     रिवाज
    0.31
     ווע
    0.31
    POSITIVE LOGITS
     forward
    1.95
     outwards
    1.73
     inwards
    1.66
     inward
    1.62
     upwards
    1.59
     outward
    1.57
     upward
    1.54
     вперед
    1.52
     downwards
    1.51
     towards
    1.48
    Act Density 0.116%

    No Known Activations