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

    Neuronpedia

    INDEX
    Explanations

    descriptions of the alignment and orientation of physical systems in a multi-dimensional space

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

    Refers to axes in a coordinate system

    np_acts-logits-general · gemini-2.0-flash

    x, y, z axes and directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.54
    RegressionTest
    -0.50
    ANDUM
    -0.48
     فريبيس
    -0.48
    TagMode
    -0.47
    hieu
    -0.47
    GeoNames
    -0.46
    Hentet
    -0.46
    GIH
    -0.45
    aiso
    -0.44
    POSITIVE LOGITS
     horizontal
    1.05
     vertical
    1.01
     axis
    1.01
     x
    1.00
    XY
    0.96
     X
    0.96
    xy
    0.96
     Y
    0.92
     xy
    0.91
    horizontal
    0.90
    Act Density 0.709%

    No Known Activations