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

    Neuronpedia

    INDEX
    Explanations

    autonomous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     water
    0.48
     to
    0.47
     negated
    0.46
     had
    0.46
     snapped
    0.45
     the
    0.44
     chemicals
    0.43
     chlorine
    0.43
    で
    0.43
    rate
    0.42
    POSITIVE LOGITS
     autonome
    0.54
    Autonomous
    0.52
     autonom
    0.50
     لديك
    0.49
     دماغ
    0.49
     multidiscipl
    0.48
     autonomous
    0.46
     cuidadosamente
    0.45
     Autonomous
    0.45
    autonomous
    0.45
    Act Density 0.002%

    No Known Activations