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

    Neuronpedia

    INDEX
    Explanations

    energy levels and balance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ioon
    0.59
    elingen
    0.57
    agascar
    0.53
    टान
    0.53
    omt
    0.53
    वालों
    0.52
    learner
    0.50
    ैट
    0.50
    ircon
    0.49
    incs
    0.49
    POSITIVE LOGITS
     energy
    1.91
     energía
    1.76
     energia
    1.73
     Energy
    1.71
    Energy
    1.60
     energie
    1.59
     ENERGY
    1.55
    エネルギー
    1.54
     Energie
    1.53
     에너지
    1.53
    Act Density 0.113%

    No Known Activations