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

    Neuronpedia

    INDEX
    Explanations

    numerical comparison and equality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     softmax
    1.27
     computes
    1.16
     Tensorflow
    1.10
     holomorphic
    1.07
     calculation
    1.06
     Jacobian
    1.05
     IEEE
    1.04
     computations
    1.03
     calcule
    1.02
     computation
    1.01
    POSITIVE LOGITS
     Kindergarten
    0.98
     kindergarten
    0.95
     kinderg
    0.87
    視覺
    0.82
    视觉
    0.79
     Pizza
    0.77
     Olimp
    0.73
     pizza
    0.72
     Oriente
    0.71
     الاجتما
    0.71
    Act Density 0.241%

    No Known Activations