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

    Neuronpedia

    INDEX
    Explanations

    increment and assignment operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ábamos
    0.71
    वर्गीय
    0.68
    lie
    0.66
     গিয়েছিল
    0.66
    ict
    0.65
    ()['
    0.65
    ()["
    0.64
     gewesen
    0.64
     এসেছিল
    0.64
     গিয়েছিল
    0.64
    POSITIVE LOGITS
     +=
    2.73
    ++;
    2.34
    +=
    2.24
     ++
    2.18
    ++
    2.02
    ++)
    1.99
    ++,
    1.99
     -=
    1.99
     ++;
    1.98
     *=
    1.83
    Act Density 0.382%

    No Known Activations