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

    Neuronpedia

    INDEX
    Explanations

    past performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     governance
    0.52
     solidification
    0.48
     pallet
    0.45
     progressBar
    0.44
     Governance
    0.42
     puberty
    0.42
     masculinity
    0.42
     lichen
    0.41
     morality
    0.41
     validation
    0.40
    POSITIVE LOGITS
     past
    0.91
    past
    0.90
    Past
    0.89
     Past
    0.88
     PAST
    0.81
    过去的
    0.79
    過去
    0.77
     الماضي
    0.74
    过去
    0.71
     گذشته
    0.70
    Act Density 0.003%

    No Known Activations