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

    Neuronpedia

    INDEX
    Explanations

    lemma, guard, provides, indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ચ
    0.45
     прогно
    0.45
     прогноз
    0.43
    年会
    0.42
     चैंपियनशिप
    0.40
     civilized
    0.40
     политика
    0.40
    alian
    0.40
    Lai
    0.39
     அர
    0.39
    POSITIVE LOGITS
     helper
    0.47
     leukaemia
    0.43
     linebacker
    0.42
     strangled
    0.40
     Linux
    0.40
     ሌ
    0.40
     bø
    0.40
     kleiner
    0.39
     Intermediate
    0.39
     intermediate
    0.39
    Act Density 0.004%

    No Known Activations