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

    Neuronpedia

    INDEX
    Explanations

    PyQt/PySide imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    So
    0.41
    ب
    0.41
    ح
    0.41
    7
    0.39
    6
    0.39
    Al
    0.39
    ก
    0.38
    ता
    0.37
    अन
    0.37
     sweetened
    0.37
    POSITIVE LOGITS
    ahili
    0.39
    ritt
    0.39
     компаний
    0.38
     អ្នក
    0.37
    lors
    0.37
    StoredKeys
    0.37
     ờ
    0.37
     ながら
    0.37
    合った
    0.37
    }$')
    0.37
    Act Density 0.005%

    No Known Activations