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

    Neuronpedia

    INDEX
    Explanations

    terms related to direction or orientation

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

    direction sensitive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sintético
    -0.52
     Económica
    -0.50
     Púb
    -0.48
     húmedo
    -0.46
     orgánico
    -0.46
    seamnă
    -0.46
     doméstico
    -0.45
     Públicas
    -0.45
    IFORN
    -0.43
     marinho
    -0.43
    POSITIVE LOGITS
     direction
    1.23
     Direction
    1.16
     Directions
    1.10
     directions
    1.09
     DIRECTION
    1.07
    irection
    1.07
    direction
    1.05
    Direction
    1.05
    directions
    0.91
    DIRECTION
    0.90
    Act Density 0.013%

    No Known Activations