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

    Neuronpedia

    INDEX
    Explanations

    neural network layers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۳
    1.00
     yanlı
    0.95
     ۳
    0.94
     rozwiąz
    0.89
     оружи
    0.89
    swadian
    0.89
     filo
    0.88
     currants
    0.88
     deewana
    0.88
    ３
    0.88
    POSITIVE LOGITS
    S
    1.41
    F
    1.37
    K
    1.29
    N
    1.25
    M
    1.24
     in
    1.23
    D
    1.23
    O
    1.23
    在
    1.22
    L
    1.09
    Act Density 0.012%

    No Known Activations