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

    Neuronpedia

    INDEX
    Explanations

    save the code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offrir
    0.41
    Genre
    0.41
    прос
    0.39
     moan
    0.38
    VIDED
    0.37
     filtro
    0.37
     vostre
    0.37
    氛
    0.37
    Genres
    0.36
     तुमचे
    0.36
    POSITIVE LOGITS
     Please
    0.63
     please
    0.55
    请
    0.50
    Please
    0.49
    please
    0.47
    請
    0.46
     Simply
    0.43
     請
    0.41
     कृपया
    0.41
     Bitte
    0.40
    Act Density 0.005%

    No Known Activations