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

    Neuronpedia

    INDEX
    Explanations

    capabilities arising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     лежа
    0.39
    Hemat
    0.39
     logic
    0.39
     лежит
    0.38
    国の
    0.38
    꼼
    0.38
    गरी
    0.37
     textbook
    0.37
     pelaku
    0.37
    izat
    0.37
    POSITIVE LOGITS
    ডেন
    0.42
     आंब
    0.40
    潮
    0.39
     Polis
    0.38
     aven
    0.37
    jež
    0.37
    }}^{(
    0.36
    ="../../../../
    0.36
     ступен
    0.36
    partitions
    0.36
    Act Density 0.000%

    No Known Activations