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

    Neuronpedia

    INDEX
    Explanations

    special events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्रेट
    0.42
    Nella
    0.38
     гос
    0.38
     боли
    0.37
    регистри
    0.37
    ्हे
    0.37
    ⁢</
    0.36
     Oc
    0.36
     Phát
    0.36
     adott
    0.35
    POSITIVE LOGITS
    cers
    0.39
     jde
    0.39
     равно
    0.39
    ouns
    0.39
     स्ट्रीमिंग
    0.38
    dst
    0.38
    gid
    0.38
    чном
    0.38
    tor
    0.38
    kst
    0.38
    Act Density 0.008%

    No Known Activations