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

    Neuronpedia

    INDEX
    Explanations

    angular direction spectra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Landau
    0.44
     计算
    0.43
    Landau
    0.42
     perhitungan
    0.41
    atol
    0.41
    oup
    0.40
     टकराव
    0.39
    óg
    0.39
     Interaction
    0.39
    perturbative
    0.39
    POSITIVE LOGITS
    angular
    0.53
     quadrant
    0.52
     angular
    0.50
    Angular
    0.49
     Angular
    0.47
     spectra
    0.46
     azimuth
    0.45
    spectra
    0.45
     directional
    0.43
    মন
    0.43
    Act Density 0.009%

    No Known Activations