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

    Neuronpedia

    INDEX
    Explanations

    grams and milligrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    emp
    0.22
    Emp
    0.20
     szeptember
    0.19
    lcc
    0.18
     empowering
    0.17
    데일리
    0.17
     óta
    0.16
    ច្
    0.16
     опу
    0.16
     нарушения
    0.16
    POSITIVE LOGITS
     nahin
    0.20
     پل
    0.19
    ☸
    0.18
     optimum
    0.18
    zków
    0.17
    bare
    0.17
     కని
    0.17
    ဆင့်
    0.17
    kowego
    0.17
     Saturdays
    0.17
    Act Density 0.005%

    No Known Activations