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

    Neuronpedia

    INDEX
    Explanations

    power dynamics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Power
    1.01
     powering
    0.95
    Power
    0.95
     Powered
    0.94
    powered
    0.93
     powered
    0.93
    Powered
    0.92
    POWER
    0.90
     POWER
    0.89
     Powers
    0.89
    POSITIVE LOGITS
     immense
    0.52
     enormous
    0.46
     сосредото
    0.43
     economic
    0.42
     concentrated
    0.42
     absolute
    0.41
    absolute
    0.41
     Absolute
    0.41
    Absolute
    0.40
    绝对
    0.40
    Act Density 0.024%

    No Known Activations