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

    Neuronpedia

    INDEX
    Explanations

    depends on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    csak
    0.51
    立场
    0.46
     лишь
    0.44
    0.43
     लड़ाई
    0.43
     बालकनियां
    0.42
     गिफ्ट
    0.42
    灘
    0.42
     только
    0.41
     පමණ
    0.41
    POSITIVE LOGITS
     rates
    0.58
     rate
    0.54
     emerges
    0.52
    Whether
    0.50
    actual
    0.49
     Whether
    0.47
    Actual
    0.47
    Rate
    0.46
    rate
    0.46
     depends
    0.46
    Act Density 0.001%

    No Known Activations