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

    Neuronpedia

    INDEX
    Explanations

    underlying concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     приступи
    0.99
     FutureWarning
    0.89
     onset
    0.88
     aprile
    0.87
    tract
    0.86
    inkle
    0.84
     tasso
    0.84
    vat
    0.83
    ابعه
    0.83
    extractor
    0.83
    POSITIVE LOGITS
    neath
    2.21
    utilized
    1.67
    estimating
    1.62
    nourished
    1.49
    appreciated
    1.47
     circumstances
    1.35
    secretary
    1.33
     guise
    1.32
    represented
    1.31
    lings
    1.31
    Act Density 0.071%

    No Known Activations