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

    Neuronpedia

    INDEX
    Explanations

    programming function signatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ❊
    0.42
     Seit
    0.42
     सॉफ्ट
    0.40
    xam
    0.40
    emote
    0.39
    ழ்த்த
    0.39
     ವರ್ಗ
    0.38
     સરળ
    0.38
     مطابق
    0.38
    arduino
    0.37
    POSITIVE LOGITS
     laine
    0.44
     apare
    0.42
     lac
    0.42
    কাল
    0.41
     leg
    0.41
     fry
    0.40
     wash
    0.39
     raiz
    0.39
     pail
    0.39
     rat
    0.38
    Act Density 0.021%

    No Known Activations