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

    Neuronpedia

    INDEX
    Explanations

    routing, screening, card, torso, trophic factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dakkh
    1.27
     vadati
    1.24
     nigris
    1.23
    รวม
    1.23
    싶
    1.21
    ‌ها
    1.19
    暠
    1.15
     gahet
    1.14
     sabbam
    1.13
    해야
    1.10
    POSITIVE LOGITS
    ી
    1.07
    1.06
    ه
    1.06
    ților
    1.05
    ക്ക്
    1.03
    java
    1.02
    our
    0.95
    orphous
    0.95
    ло
    0.95
    лин
    0.94
    Act Density 0.000%

    No Known Activations