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

    Neuronpedia

    INDEX
    Explanations

    <!DOCTYPE html>

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }]=
    0.42
    larını
    0.41
     स्वाभाविक
    0.41
     cinética
    0.40
    釵
    0.40
     afirmar
    0.39
    éntesis
    0.39
    fromj
    0.39
    lerin
    0.38
     alimento
    0.38
    POSITIVE LOGITS
    x
    0.48
     t
    0.42
    ↵
    0.41
    ad
    0.40
     x
    0.40
     th
    0.39
    [
    0.39
    高
    0.39
     小
    0.39
    n
    0.39
    Act Density 0.010%

    No Known Activations