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

    Neuronpedia

    INDEX
    Explanations

    give me your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Despatx
    0.54
     dwRes
    0.50
    dade
    0.47
    custList
    0.47
    वाड़ी
    0.47
    filenames
    0.46
    dai
    0.45
     ሥራ
    0.45
     آئی
    0.45
     تلیفون
    0.45
    POSITIVE LOGITS
     on
    0.55
     It
    0.53
     in
    0.52
     On
    0.52
     type
    0.50
    类型的
    0.50
     typu
    0.48
    胧
    0.47
     >
    0.47
     ot
    0.46
    Act Density 0.000%

    No Known Activations