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

    Neuronpedia

    INDEX
    Explanations

    rotary-wing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rew
    0.44
     إلا
    0.41
     канализа
    0.39
     incont
    0.39
     cidades
    0.39
     minerales
    0.39
     urbana
    0.39
    जिन
    0.38
     перейти
    0.38
    ិត្ត
    0.38
    POSITIVE LOGITS
     Treaty
    0.44
     Futures
    0.42
    Ａ
    0.42
    数字
    0.40
    CCC
    0.40
     Disk
    0.39
    Argent
    0.38
     যুক্তরাষ্ট্রের
    0.38
    端
    0.38
    Americans
    0.38
    Act Density 0.001%

    No Known Activations