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

    Neuronpedia

    INDEX
    Explanations

    end took

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    D
    0.48
    J
    0.47
    F
    0.45
    I
    0.43
     commentary
    0.42
    ruce
    0.42
     crowding
    0.42
     accreditation
    0.42
    K
    0.42
    E
    0.41
    POSITIVE LOGITS
     prodotti
    0.46
    ͐
    0.46
    нициа
    0.45
    לך
    0.45
    ради
    0.45
    ী
    0.45
    支持
    0.44
    στο
    0.44
    готовка
    0.44
    явления
    0.43
    Act Density 0.000%

    No Known Activations