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

    Neuronpedia

    INDEX
    Explanations

    getting up and leaving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    онів
    0.40
     specific
    0.40
     chun
    0.39
     peaceful
    0.39
    قليم
    0.38
     chopper
    0.38
     SPEC
    0.37
     technological
    0.37
     fruits
    0.36
    SPEC
    0.36
    POSITIVE LOGITS
     வெளியே
    0.52
     keluar
    0.51
     выйти
    0.48
    起身
    0.48
     dậy
    0.47
    离开了
    0.47
     выход
    0.47
    ออกจาก
    0.46
     вышла
    0.46
    离开
    0.45
    Act Density 0.037%

    No Known Activations