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

    Neuronpedia

    INDEX
    Explanations

    Option 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mith
    0.55
    raum
    0.52
    rául
    0.49
    mette
    0.49
    mart
    0.48
    flächen
    0.47
     পিছ
    0.47
     אחר
    0.47
    鄒
    0.47
    ienne
    0.46
    POSITIVE LOGITS
    ের
    0.48
    OA
    0.48
    до
    0.47
    ેલા
    0.44
    дки
    0.43
     thickening
    0.42
    ㎝
    0.42
    <0x80>
    0.42
    нд
    0.42
    ँसी
    0.41
    Act Density 0.111%

    No Known Activations