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

    Neuronpedia

    INDEX
    Explanations

    methods description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ção
    0.66
    los
    0.66
    กำลัง
    0.63
    يا
    0.60
     সংরক্ষণ
    0.60
    siniz
    0.59
    ział
    0.59
    |$,
    0.58
    тена
    0.57
    ği
    0.57
    POSITIVE LOGITS
    ,
    0.66
     diagon
    0.62
     mamma
    0.60
    Deps
    0.60
     atyp
    0.59
     بۆ
    0.58
     kuri
    0.57
    ่า
    0.57
    Respond
    0.57
    र
    0.56
    Act Density 0.000%

    No Known Activations