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

    Neuronpedia

    INDEX
    Explanations

    natural bodies of water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gegevens
    0.71
     organs
    0.70
     electronics
    0.70
    Nk
    0.70
    iyaç
    0.70
     multitude
    0.69
    饽
    0.68
     maddenin
    0.66
     necessidades
    0.66
     druge
    0.66
    POSITIVE LOGITS
    Mountains
    0.56
    ውነተኛ
    0.53
    Alright
    0.53
    把他
    0.53
    pH
    0.52
    دا
    0.51
    時間
    0.51
    ج
    0.51
    bend
    0.51
     كريم
    0.51
    Act Density 0.191%

    No Known Activations