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

    Neuronpedia

    INDEX
    Explanations

    sizes and fit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    熵
    0.60
     शक्त
    0.52
     apopt
    0.51
     HINSTANCE
    0.50
    텃
    0.49
     creatividad
    0.48
    スキル
    0.46
     neuronal
    0.46
    餌
    0.46
    neurons
    0.44
    POSITIVE LOGITS
     fit
    0.92
     Fit
    0.83
     fitted
    0.81
     fitting
    0.77
    fit
    0.72
     Fitting
    0.71
     사이즈
    0.71
     measurements
    0.70
     sizes
    0.70
    fitting
    0.70
    Act Density 0.057%

    No Known Activations