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

    Neuronpedia

    INDEX
    Explanations

    text structure markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    馚
    0.47
    崗
    0.41
    ынша
    0.40
    岗位
    0.40
    Мушко
    0.40
    Huff
    0.39
     النرويج
    0.39
    ถมศึกษา
    0.39
    đi
    0.38
     redness
    0.38
    POSITIVE LOGITS
    encour
    0.41
    挨
    0.38
     받는
    0.37
    uu
    0.37
     अणु
    0.37
    encoded
    0.36
    includes
    0.36
     erk
    0.36
    Aik
    0.36
    commun
    0.34
    Act Density 0.000%

    No Known Activations