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

    Neuronpedia

    INDEX
    Explanations

    anytime soon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Spare
    0.44
    Leg
    0.42
    Transparent
    0.38
     transparencia
    0.38
     Leg
    0.38
     UNION
    0.38
     tách
    0.38
     transparente
    0.37
     Spare
    0.37
     obstructed
    0.37
    POSITIVE LOGITS
     reset
    0.60
     close
    0.56
    close
    0.55
     closeModal
    0.52
     Close
    0.52
    reset
    0.50
     Reset
    0.49
     resetting
    0.49
    Close
    0.46
     resets
    0.45
    Act Density 0.000%

    No Known Activations