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

    Neuronpedia

    INDEX
    Explanations

    direction and onward movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     áreas
    0.44
     halts
    0.41
     ở
    0.41
     आयी
    0.41
    回來
    0.41
     వద్ద
    0.40
     stopped
    0.39
     máximo
    0.39
     stops
    0.39
     parked
    0.38
    POSITIVE LOGITS
     westward
    0.66
     northward
    0.64
     eastward
    0.62
     southward
    0.60
     onwards
    0.59
     onward
    0.59
     outgoing
    0.57
     outbound
    0.55
    向
    0.54
     exported
    0.52
    Act Density 0.109%

    No Known Activations