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

    Neuronpedia

    INDEX
    Explanations

    program, components, Call, genetic, current

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    מ
    0.80
     custodian
    0.76
    не
    0.72
     ע
    0.71
     documental
    0.71
     제대로
    0.70
    явление
    0.70
     ਇ
    0.70
    ната
    0.69
    ма
    0.69
    POSITIVE LOGITS
     kucing
    0.88
    apped
    0.79
     mares
    0.79
    soluble
    0.78
     dovuto
    0.73
    fowl
    0.73
    arget
    0.72
    ikk
    0.71
    ily
    0.71
    ischen
    0.71
    Act Density 0.012%

    No Known Activations