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

    Neuronpedia

    INDEX
    Explanations

    targeted contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    पया
    0.51
    ćem
    0.49
     மீட்ட
    0.48
     স্নাত
    0.47
    <unused675>
    0.47
    玺
    0.46
     мое
    0.46
    destino
    0.46
     ಮ
    0.45
     иностран
    0.44
    POSITIVE LOGITS
     values
    0.51
     until
    0.50
     (>
    0.50
     (
    0.47
     targeting
    0.46
     min
    0.46
     interval
    0.45
     code
    0.45
     sequence
    0.45
     ratio
    0.44
    Act Density 0.002%

    No Known Activations