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

    Neuronpedia

    INDEX
    Explanations

    PyTorch machine learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    斃
    0.40
     Tasmanian
    0.40
    layoutWidget
    0.39
     Ctrl
    0.38
    }}}{\
    0.38
    驄
    0.37
     recurring
    0.37
    elius
    0.37
     wasting
    0.37
    اتا
    0.36
    POSITIVE LOGITS
    Py
    0.89
     Py
    0.87
     py
    0.85
     pyt
    0.72
     PY
    0.70
    Torch
    0.66
    thia
    0.66
    PY
    0.65
    py
    0.63
    thon
    0.61
    Act Density 0.010%

    No Known Activations