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

    Neuronpedia

    INDEX
    Explanations

    deep learning and neural networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     về
    0.80
     rừng
    0.70
    ары
    0.68
     từ
    0.67
     жөнүндө
    0.67
     بارے
    0.66
     నా
    0.66
     hồ
    0.66
     nhà
    0.65
     लिह
    0.65
    POSITIVE LOGITS
    Neural
    0.73
     Neural
    0.68
    Ambient
    0.63
     softmax
    0.62
    keras
    0.61
    ="
    0.61
    Optim
    0.61
    Tensor
    0.60
    softmax
    0.59
    ymmetric
    0.58
    Act Density 1.214%

    No Known Activations