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

    Neuronpedia

    INDEX
    Explanations

    terms related to direction in a spatial or visual context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    direction of position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.50
     мәкал
    -0.44
     contextLoads
    -0.44
     newArray
    -0.44
    ſelves
    -0.43
     pulumi
    -0.43
    centralwidget
    -0.42
     nakalista
    -0.42
    JspWriter
    -0.41
    seamnă
    -0.41
    POSITIVE LOGITS
    Direction
    2.81
     Direction
    2.42
    direction
    2.17
    DIRECTION
    2.05
     DIRECTION
    1.99
     direction
    1.97
     Directions
    1.67
    Directions
    1.59
     directions
    1.56
    directions
    1.52
    Act Density 0.006%

    No Known Activations