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

    Neuronpedia

    INDEX
    Explanations

    a pretty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    加熱
    0.43
     Shabbat
    0.41
    museum
    0.40
     Integr
    0.39
    加热
    0.38
     sket
    0.38
     Integrative
    0.38
     Indonesia
    0.37
    ুখ
    0.37
     JSONObject
    0.37
    POSITIVE LOGITS
     नाबालिग
    0.47
     prohibits
    0.42
     resides
    0.40
    ानीय
    0.39
     overcome
    0.39
     urbana
    0.39
     reside
    0.38
     Sayles
    0.38
     acres
    0.38
     relieves
    0.38
    Act Density 0.000%

    No Known Activations