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

    Neuronpedia

    INDEX
    Explanations

    gradual progression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intra
    0.57
    ation
    0.55
     encore
    0.52
    நட
    0.52
    ator
    0.51
     ಘೋಷ
    0.49
    ailable
    0.49
    ૭
    0.49
    rufen
    0.49
    ्रीम
    0.48
    POSITIVE LOGITS
     eventually
    1.81
     gradually
    1.80
    随着
    1.76
     Eventually
    1.73
    逐渐
    1.69
    Eventually
    1.69
    渐渐
    1.67
     dần
    1.62
    逐漸
    1.57
     progressively
    1.56
    Act Density 0.690%

    No Known Activations