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

    Neuronpedia

    INDEX
    Explanations

    modules and packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inté
    0.52
     Ducati
    0.51
     Daimler
    0.47
    <0x8A>
    0.47
     neuronal
    0.46
     уравнения
    0.46
     Triple
    0.45
    ნა
    0.45
     Nissan
    0.45
     beant
    0.45
    POSITIVE LOGITS
    वर्षी
    0.45
    व
    0.45
    ियमित
    0.44
    ur
    0.43
    Una
    0.42
    scaled
    0.42
     sprawl
    0.42
    हर
    0.41
    તાવ
    0.41
     श्रेणियों
    0.41
    Act Density 0.001%

    No Known Activations