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

    Neuronpedia

    INDEX
    Explanations

    state changing operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     testifies
    0.96
     congruent
    0.89
     Mild
    0.88
     Cretaceous
    0.88
     Pleistocene
    0.87
     ASCII
    0.85
     ≥
    0.84
     Pilates
    0.83
     monumental
    0.82
     ($\
    0.82
    POSITIVE LOGITS
    initialize
    1.51
    Initialize
    1.31
    initialized
    1.28
    enable
    1.26
    update
    1.25
    init
    1.23
    disable
    1.22
    startTime
    1.17
    refresh
    1.15
     initialize
    1.15
    Act Density 0.592%

    No Known Activations