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

    Neuronpedia

    INDEX
    Explanations

    items in a list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ität
    0.31
    ágenes
    0.27
    தியின்
    0.24
    ेंगू
    0.22
    "}
    0.21
    গত
    0.21
     సమస్య
    0.21
    "{
    0.21
     thesis
    0.21
    进程
    0.21
    POSITIVE LOGITS
    preferably
    0.30
    または
    0.29
     plus
    0.28
     resistente
    0.28
     અથવા
    0.28
     insieme
    0.27
     ASAP
    0.27
     preferably
    0.27
    和一个
    0.27
     또는
    0.27
    Act Density 0.101%

    No Known Activations