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

    Neuronpedia

    INDEX
    Explanations

    comparing or listing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     momentous
    0.42
    җ
    0.41
     واپس
    0.39
     envisaged
    0.39
     Choibalsan
    0.39
    ísmo
    0.39
     aspirations
    0.38
     Bh
    0.38
     заинтере
    0.38
     bhan
    0.38
    POSITIVE LOGITS
     compared
    0.48
    "。
    0.44
    compared
    0.43
    Pray
    0.42
     Compared
    0.42
    Par
    0.42
    Gray
    0.42
    Crop
    0.40
    Pens
    0.39
    Compared
    0.39
    Act Density 0.007%

    No Known Activations