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

    Neuronpedia

    INDEX
    Explanations

    interpolating sequences or float

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gleich
    -0.77
    cuti
    -0.74
     Coc
    -0.73
    дьми
    -0.73
    knię
    -0.72
    besar
    -0.71
     exfoli
    -0.71
    ொ
    -0.70
    peugeot
    -0.70
    urkan
    -0.70
    POSITIVE LOGITS
     interpolation
    3.33
     Interpolation
    2.88
     interpol
    2.86
    interpolation
    2.72
     interpolate
    2.66
    Interpolation
    2.55
     interpolated
    2.48
    interp
    2.31
     interp
    2.28
    interpolate
    2.27
    Act Density 0.027%

    No Known Activations