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

    Neuronpedia

    INDEX
    Explanations

    plastic key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     weiteren
    1.20
    %、
    1.14
    inescence
    1.07
    tt
    1.07
    ม
    1.06
    ১২
    1.05
     entstanden
    1.04
    ारे
    1.04
     начинается
    1.02
     αρχ
    1.02
    POSITIVE LOGITS
    ो
    1.36
     equival
    1.22
    quele
    1.15
    que
    1.14
    ছু
    1.13
    ра
    1.09
     уча
    1.08
    Ricardo
    1.07
    ри
    1.07
    ЛЕ
    1.05
    Act Density 0.001%

    No Known Activations