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

    Neuronpedia

    INDEX
    Explanations

    resource types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ປະ
    0.40
     procent
    0.40
    leyball
    0.40
     डिफर
    0.39
     ग्रेट
    0.38
     मीन
    0.37
    igold
    0.36
     উপদে
    0.36
    пециа
    0.35
    ALLOWED
    0.35
    POSITIVE LOGITS
    <b>
    0.41
     użyt
    0.41
    </i>
    0.37
    <unused35>
    0.37
    </b>
    0.37
    bubble
    0.36
     Lincoln
    0.35
     Optical
    0.35
     przechowy
    0.35
    があり
    0.34
    Act Density 0.038%

    No Known Activations