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

    Neuronpedia

    INDEX
    Explanations

    different contexts and situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shim
    0.38
    ñas
    0.38
     brought
    0.37
     náv
    0.36
    هُ
    0.36
     tengamos
    0.36
     previously
    0.35
     Shrewsbury
    0.35
    ্বক
    0.35
    eyi
    0.34
    POSITIVE LOGITS
     кри
    0.39
     aggregates
    0.38
    嚗
    0.38
    叅
    0.37
    Aqu
    0.37
     পাকিস্তানীরা
    0.37
    ncols
    0.36
    LANG
    0.36
     //@
    0.36
    мей
    0.35
    Act Density 0.002%

    No Known Activations