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

    Neuronpedia

    INDEX
    Explanations

    percentage points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inco
    0.44
     yağ
    0.40
     Particle
    0.38
    സ്ത
    0.38
    绥
    0.38
    മാണ്
    0.38
    DOF
    0.37
    നിയ
    0.37
     lai
    0.37
     Reactive
    0.37
    POSITIVE LOGITS
     points
    1.08
    points
    1.07
    Points
    1.01
     puntos
    0.95
     Points
    0.89
     POINTS
    0.87
     Punkten
    0.83
     pontos
    0.81
    percentage
    0.80
    POINTS
    0.80
    Act Density 0.007%

    No Known Activations