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

    Neuronpedia

    INDEX
    Explanations

    format, Berlin, citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maggiore
    0.47
    }^{(
    0.47
    診断
    0.46
     ખો
    0.46
    '_
    0.46
     питания
    0.45
    ับ
    0.45
     از
    0.45
    '}$
    0.45
    дня
    0.44
    POSITIVE LOGITS
    Α
    0.57
    Σ
    0.57
    ström
    0.49
    Another
    0.48
     Study
    0.48
     verlei
    0.48
    ξει
    0.47
    zik
    0.47
    née
    0.47
     Thesis
    0.46
    Act Density 0.000%

    No Known Activations