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

    Neuronpedia

    INDEX
    Explanations

    but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nc
    0.17
    W
    0.17
    Z
    0.16
    xious
    0.16
    iyordu
    0.16
    O
    0.16
    L
    0.16
    ohms
    0.16
    P
    0.16
    Q
    0.16
    POSITIVE LOGITS
    on
    0.25
     될
    0.17
    д
    0.16
    นาม
    0.16
     développement
    0.15
    d
    0.15
    a
    0.15
     که
    0.15
     되는
    0.14
    า
    0.14
    Act Density 0.000%

    No Known Activations