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

    Neuronpedia

    INDEX
    Explanations

    references to measurements and physical properties related to motion and stability in a scientific context

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

    Direction or orientation

    np_acts-logits-general · gemini-2.0-flash

    spatial direction and orientation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +:+
    -0.50
    Personensuche
    -0.49
     elite
    -0.45
     '~
    -0.45
     mark
    -0.45
     mou
    -0.45
     cache
    -0.45
    astify
    -0.44
    thumb
    -0.44
     thumb
    -0.43
    POSITIVE LOGITS
     vertically
    0.84
     perpendicular
    0.78
     vertical
    0.78
     lengthwise
    0.74
     verticale
    0.74
     horizontally
    0.72
     orthogonal
    0.71
     horizontal
    0.70
     axis
    0.69
    Vertical
    0.69
    Act Density 0.926%

    No Known Activations