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

    Neuronpedia

    INDEX
    Explanations

    legal recitals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    লেখা
    0.41
     geno
    0.38
    STO
    0.37
    шем
    0.37
     Excluding
    0.37
     ප්‍රති
    0.36
     পাথ
    0.36
    ρα
    0.35
     reply
    0.35
    াণী
    0.35
    POSITIVE LOGITS
    Whereas
    0.72
    WHEREAS
    0.67
     Whereas
    0.65
    whereas
    0.64
     whereas
    0.57
     WHERE
    0.52
     justifying
    0.50
     обосно
    0.48
     rationale
    0.46
    而
    0.46
    Act Density 0.006%

    No Known Activations