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

    Neuronpedia

    INDEX
    Explanations

    reporting numerical percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ير
    0.38
    ɔ
    0.38
    滹
    0.36
    ৈত্র
    0.35
    globin
    0.34
    ក្ត
    0.34
     такую
    0.34
     mags
    0.34
     împ
    0.33
     gobier
    0.33
    POSITIVE LOGITS
     waiting
    0.41
     repeat
    0.41
    CONFIGURE
    0.40
    waiting
    0.40
    CREATE
    0.38
    ordinary
    0.37
    宣布
    0.37
     challenge
    0.37
     vra
    0.37
     زمان
    0.37
    Act Density 0.001%

    No Known Activations