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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ＼↵
    -0.07
     kne
    -0.07
    BBBB
    -0.07
     vào
    -0.07
    ेखन
    -0.06
     sheds
    -0.06
     ΕΠ
    -0.06
     جون
    -0.06
     Urban
    -0.06
     uvád
    -0.06
    POSITIVE LOGITS
     static
    0.06
     стратег
    0.06
    ocos
    0.06
     onOptionsItemSelected
    0.06
    idade
    0.06
    основ
    0.06
    inished
    0.06
    Toolkit
    0.06
    idente
    0.06
    _dict
    0.06
    Act Density 0.005%

    No Known Activations