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

    Neuronpedia

    INDEX
    Explanations

    time and timing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Moment
    0.46
    же
    0.43
     tim
    0.42
     fired
    0.40
     suivante
    0.40
     tym
    0.39
    ágenes
    0.39
     時
    0.39
     时
    0.39
    时刻
    0.38
    POSITIVE LOGITS
     libre
    0.64
     libres
    0.53
     livre
    0.52
     آزاد
    0.50
     prud
    0.47
     Libre
    0.46
    libre
    0.45
     morts
    0.44
     devoting
    0.42
     dedic
    0.41
    Act Density 0.005%

    No Known Activations