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

    Neuronpedia

    INDEX
    Explanations

    truly emotionally, dressing modestly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Whilst
    0.49
    বধূ
    0.47
    اً
    0.46
    flatiron
    0.46
    ے۔
    0.45
    ೆಯನ್ನು
    0.45
    xmlns
    0.44
     首先
    0.44
     虽然
    0.44
    DbType
    0.44
    POSITIVE LOGITS
     attainable
    0.54
     cellules
    0.49
    inching
    0.48
    wig
    0.46
    人間の
    0.46
     clumps
    0.46
     achievable
    0.46
    เมื่อ
    0.46
    lapping
    0.45
     tractable
    0.45
    Act Density 0.000%

    No Known Activations