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

    Neuronpedia

    INDEX
    Explanations

    define practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     гуляць
    0.44
    Przypisy
    0.43
    愆
    0.41
    들의
    0.41
    鎶
    0.41
     studie
    0.40
    ท่อง
    0.40
     일부
    0.40
     pollut
    0.39
     miejsc
    0.39
    POSITIVE LOGITS
     tactics
    0.41
    連
    0.40
     sekar
    0.38
    rategy
    0.38
     defines
    0.38
     aspires
    0.37
    紅色
    0.37
    VISION
    0.36
     Tactics
    0.36
     intends
    0.36
    Act Density 0.000%

    No Known Activations