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

    Neuronpedia

    INDEX
    Explanations

    speaker attribution after quotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.82
    /
    0.72
    }?
    0.69
    (
    0.66
    :(
    0.64
    :")
    0.63
    :<
    0.62
    Segments
    0.61
    :"
    0.61
     تم
    0.61
    POSITIVE LOGITS
    他说
    1.54
     said
    1.53
     says
    1.48
    她说
    1.39
    他說
    1.27
    said
    1.24
     сказала
    1.19
     explained
    1.18
     säger
    1.17
    says
    1.17
    Act Density 0.033%

    No Known Activations