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

    Neuronpedia

    INDEX
    Explanations

    shading, blending, and color variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     birefringence
    0.87
     orthonormal
    0.76
     microbi
    0.76
     képes
    0.75
     bioinformatics
    0.75
    ukary
    0.74
    FileWriter
    0.72
     gyroscope
    0.72
    tsioon
    0.71
     おり
    0.71
    POSITIVE LOGITS
     blending
    1.16
     blends
    1.06
    Blending
    1.05
     blend
    1.04
     lighten
    1.02
     Blend
    1.01
     blended
    0.98
     highlights
    0.97
     heavier
    0.96
    Blend
    0.95
    Act Density 0.142%

    No Known Activations