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

    Neuronpedia

    INDEX
    Explanations

    `:**` delimiter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ")))
    1.10
     Because
    1.09
     because
    1.04
    ')))
    0.97
     puisque
    0.96
     BECAUSE
    0.95
     因為
    0.93
    because
    0.92
    ']))
    0.90
     क्योंकि
    0.90
    POSITIVE LOGITS
    শ্
    0.89
    (
    0.84
    <em>
    0.80
     bilder
    0.79
    <strong>
    0.77
    ,
    0.76
    -
    0.75
     piy
    0.75
     krok
    0.74
    త్ప
    0.74
    Act Density 0.125%

    No Known Activations