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

    Neuronpedia

    INDEX
    Explanations

    estimates and figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    あとは
    0.43
     প্রাধান্য
    0.43
     incomplète
    0.41
     হউক
    0.40
    AspectRatio
    0.40
     പരിച
    0.40
     পোষণ
    0.40
    Enfin
    0.39
     ہمیشہ
    0.38
    ={(
    0.38
    POSITIVE LOGITS
     estimates
    1.52
     Estimates
    1.39
    estimates
    1.38
     according
    1.38
     According
    1.35
     estimated
    1.27
    according
    1.26
    According
    1.23
     estimate
    1.20
     según
    1.19
    Act Density 0.061%

    No Known Activations