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

    Neuronpedia

    INDEX
    Explanations

    bullet list, points, hell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atering
    0.78
     கற்க
    0.76
    鎵
    0.75
     Shandong
    0.73
    uced
    0.73
     disapproved
    0.73
    টন
    0.73
    աք
    0.73
    迭
    0.73
     Qué
    0.73
    POSITIVE LOGITS
    proof
    1.08
     journal
    0.99
    journal
    0.98
    Journal
    0.97
    storm
    0.88
     Journal
    0.88
    storms
    0.86
    PROOF
    0.83
     journaling
    0.83
     വിധ
    0.83
    Act Density 0.005%

    No Known Activations