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

    Neuronpedia

    INDEX
    Explanations

    PPP Negotiations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    পি
    0.48
    (";
    0.44
    沟
    0.44
    צו
    0.43
    妵
    0.43
    银行
    0.43
    鸰
    0.42
    終
    0.41
    ("{
    0.40
    师
    0.40
    POSITIVE LOGITS
    ification
    0.56
    ius
    0.52
    ifying
    0.49
    eers
    0.49
    iid
    0.48
    iD
    0.47
     c
    0.47
    eer
    0.47
    ar
    0.46
    iin
    0.46
    Act Density 0.001%

    No Known Activations