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

    Neuronpedia

    INDEX
    Explanations

    advice and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dernière
    0.55
    MutableArray
    0.52
    ரைப்
    0.47
     poet
    0.47
    வசம்
    0.45
    ńst
    0.45
     dinámica
    0.45
    sweet
    0.44
    íss
    0.44
     révolution
    0.44
    POSITIVE LOGITS
    +'
    0.48
     음
    0.45
    +,
    0.44
     htim
    0.42
    +.
    0.42
     izra
    0.41
     ЖК
    0.41
    其他
    0.41
     उचित
    0.41
    '',
    0.41
    Act Density 0.001%

    No Known Activations