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

    Neuronpedia

    INDEX
    Explanations

    highquality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comportamiento
    0.80
     hubungan
    0.78
    חנו
    0.76
     eril
    0.75
     kezel
    0.74
    huge
    0.73
     प्रभावों
    0.72
     mało
    0.71
    isPreview
    0.71
    हारिक
    0.70
    POSITIVE LOGITS
     stakes
    1.21
     octane
    1.19
     levels
    1.18
     altitude
    1.16
     level
    1.15
     priced
    1.12
     priority
    1.09
     quality
    1.08
     altitudes
    1.08
     intensity
    1.08
    Act Density 0.303%

    No Known Activations