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

    Neuronpedia

    INDEX
    Explanations

    introduction to a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     กรณี
    0.77
    就可以了
    0.73
    即可
    0.72
     신청
    0.71
    กรณี
    0.69
     '':
    0.69
    বিস্তারিত
    0.68
     nữa
    0.68
    .'
    0.68
    Use
    0.67
    POSITIVE LOGITS
     \%)$,
    0.71
     conscious
    0.69
    ilung
    0.69
    superclass
    0.69
     payers
    0.65
     imaging
    0.64
     lifecycle
    0.64
    োগ্র
    0.63
    लिया
    0.63
     eeu
    0.62
    Act Density 0.141%

    No Known Activations