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

    Neuronpedia

    INDEX
    Explanations

    shape and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Saving
    0.84
     maniak
    0.83
     solucionar
    0.82
    节省
    0.80
     serangan
    0.79
     bragging
    0.79
     wParam
    0.79
     Boosting
    0.78
     зло
    0.78
     insulting
    0.77
    POSITIVE LOGITS
     shaped
    2.32
     shape
    2.19
     shapes
    2.12
     shaping
    2.11
    shaped
    1.99
    shape
    1.87
    shapes
    1.80
     Shaped
    1.76
     Shape
    1.72
     Shapes
    1.64
    Act Density 0.273%

    No Known Activations