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

    Neuronpedia

    INDEX
    Explanations

    has/have with descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     イタリア
    0.12
     mesmos
    0.12
    дати
    0.12
     imong
    0.12
     valam
    0.12
     jeweil
    0.12
     különböz
    0.11
     organismo
    0.11
     انواع
    0.11
     mesmas
    0.11
    POSITIVE LOGITS
     been
    0.22
     plenty
    0.19
     enough
    0.19
     strong
    0.17
     discernible
    0.17
    been
    0.16
     ಸಾಕಷ್ಟು
    0.16
    足够的
    0.16
     extensive
    0.16
     достаточно
    0.15
    Act Density 0.120%

    No Known Activations