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

    Neuronpedia

    INDEX
    Explanations

    contradict ethical guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दिवा
    0.46
     Gra
    0.45
     Thick
    0.45
     Hebrews
    0.44
     बचे
    0.42
     Bohr
    0.41
     bewe
    0.41
     shuffle
    0.41
     fij
    0.40
     Geno
    0.40
    POSITIVE LOGITS
    rect
    0.51
    ƌ
    0.48
    ä
    0.45
    гли
    0.43
    جا
    0.43
    ї
    0.43
    ढ़
    0.43
    CCN
    0.43
    cknow
    0.42
     rất
    0.42
    Act Density 0.002%

    No Known Activations