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

    Neuronpedia

    INDEX
    Explanations

    pushing boundaries of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    텝
    1.02
    matic
    0.93
    купа
    0.86
    motivation
    0.83
     మాట
    0.83
    娉
    0.83
    っていた
    0.81
    ષા
    0.81
    vitamin
    0.80
    逻辑
    0.80
    POSITIVE LOGITS
    나
    1.15
    াচ
    1.11
    ز
    1.08
    am
    1.02
     इनोवेशन
    1.02
    Innovative
    0.99
    at
    0.98
     innovate
    0.98
     Innovative
    0.97
    Caractéristiques
    0.96
    Act Density 0.071%

    No Known Activations