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

    Neuronpedia

    INDEX
    Explanations

    discuss how or opportunities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.03
    nel
    0.85
    blic
    0.84
    tek
    0.84
    ku
    0.82
    ka
    0.82
     أ
    0.81
    ından
    0.80
     قد
    0.80
     و
    0.79
    POSITIVE LOGITS
    in
    1.88
    u
    1.48
    v
    1.37
    im
    1.20
    ів
    1.19
    ו
    1.17
    मधील
    1.13
    ות
    1.11
    inę
    1.11
    i
    1.08
    Act Density 0.012%

    No Known Activations