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

    Neuronpedia

    INDEX
    Explanations

    multitude of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    করিতে
    0.52
    رحله
    0.44
     mostrado
    0.43
    <unused410>
    0.42
    <unused971>
    0.42
    ೊಂದಿಗೆ
    0.42
     indicaciones
    0.41
    जफ्
    0.41
     primeras
    0.41
    ꗥ
    0.41
    POSITIVE LOGITS
    0.48
    ↵↵
    0.47
    ↵
    0.47
    :
    0.46
    .
    0.42
     F
    0.42
     Confucian
    0.42
     Man
    0.42
     Paradox
    0.41
     "
    0.41
    Act Density 0.034%

    No Known Activations