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

    Neuronpedia

    INDEX
    Explanations

    mentioning prior context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bahwa
    0.93
     हुए
    0.87
     rằng
    0.86
     följande
    0.84
     أنه
    0.84
     हुये
    0.82
     neh
    0.78
    一年
    0.75
     abandonar
    0.74
     warum
    0.74
    POSITIVE LOGITS
    interpre
    0.86
    标识
    0.85
     контек
    0.82
    Trivia
    0.80
    multirow
    0.80
     späteren
    0.80
    ्त
    0.78
     Commentaires
    0.77
    later
    0.77
    ἢ
    0.77
    Act Density 0.010%

    No Known Activations