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

    Neuronpedia

    INDEX
    Explanations

    maintaining things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अटक
    0.45
     pembuatan
    0.42
    ítés
    0.42
     unimportant
    0.42
     ఆలో
    0.41
    ከተ
    0.41
     richi
    0.40
     проведения
    0.39
     Bugün
    0.38
     Immediately
    0.38
    POSITIVE LOGITS
     maintain
    0.92
     유지
    0.88
    maintain
    0.88
     Maintain
    0.86
    Maintain
    0.86
     momentum
    0.84
     Maintains
    0.84
     maintains
    0.83
     Maintaining
    0.83
     homeostasis
    0.81
    Act Density 0.015%

    No Known Activations