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

    Neuronpedia

    INDEX
    Explanations

    for example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.65
    O
    0.59
    N
    0.57
    UER
    0.52
     ngunit
    0.51
    F
    0.49
     ذریع
    0.48
    oS
    0.48
    erende
    0.48
    LIS
    0.47
    POSITIVE LOGITS
     sake
    0.92
     starters
    0.72
    giveness
    0.70
     purposes
    0.65
     instance
    0.62
    ced
    0.60
     aqueles
    0.60
    1
    0.59
     example
    0.59
    cing
    0.59
    Act Density 0.034%

    No Known Activations