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

    Neuronpedia

    INDEX
    Explanations

    building custom WebViews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    خ
    0.44
    Jimmy
    0.42
    Kyr
    0.42
    Colors
    0.41
    cyber
    0.41
    Trump
    0.41
    corruption
    0.41
    Con
    0.41
     etern
    0.41
    Century
    0.40
    POSITIVE LOGITS
     smaller
    0.49
     kleinere
    0.48
     pudo
    0.46
     Bist
    0.46
     piccola
    0.46
     ámbito
    0.46
     могла
    0.46
    द्वी
    0.45
     осмо
    0.45
     района
    0.45
    Act Density 0.001%

    No Known Activations