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

    Neuronpedia

    INDEX
    Explanations

    99

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orbits
    0.90
    Ფ
    0.87
    하라
    0.85
     Ds
    0.84
    忓
    0.82
    Empleado
    0.82
    зербайд
    0.81
    치의
    0.81
     впоследствии
    0.80
    торию
    0.79
    POSITIVE LOGITS
     relaxed
    0.85
     belie
    0.83
     punctured
    0.82
    楨
    0.80
     loosened
    0.79
     easily
    0.77
     immersed
    0.75
     solito
    0.74
     scr
    0.74
     cohesive
    0.74
    Act Density 0.043%

    No Known Activations