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

    Neuronpedia

    INDEX
    Explanations

    Mathematical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     règle
    -0.08
     minuter
    -0.08
    -yard
    -0.08
    onges
    -0.08
     priorit
    -0.08
    eles
    -0.08
     ruler
    -0.08
    ponde
    -0.08
    Agg
    -0.08
     Agg
    -0.08
    POSITIVE LOGITS
     symmetry
    0.13
     symmetrical
    0.12
    sym
    0.10
     sym
    0.10
     symmetric
    0.10
     Orientation
    0.09
    rored
    0.09
     orientations
    0.08
     сим
    0.08
     orientation
    0.08
    Act Density 0.069%

    No Known Activations