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

    Neuronpedia

    INDEX
    Explanations

    disclaimers about advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    נדה
    0.34
     подска
    0.33
     வழி
    0.32
     निरा
    0.32
     semana
    0.31
    աս
    0.30
     Yep
    0.30
     cib
    0.30
    rians
    0.30
     σημαν
    0.30
    POSITIVE LOGITS
    义
    0.38
    yi
    0.37
     affair
    0.36
     necessitate
    0.36
     Hash
    0.35
     require
    0.35
    urator
    0.34
    ならでは
    0.33
    怙
    0.33
    against
    0.32
    Act Density 0.001%

    No Known Activations