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

    Neuronpedia

    INDEX
    Explanations

    tutorials, head, file, few

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    పై
    1.02
     larga
    1.02
    rift
    1.00
    ো
    0.99
    ้ำ
    0.99
     rspace
    0.98
    on
    0.97
    وپ
    0.96
    길
    0.95
    ল
    0.95
    POSITIVE LOGITS
     willful
    1.14
     deletion
    1.07
     deletions
    0.97
    idered
    0.96
     adanya
    0.96
     وكذلك
    0.96
    आन
    0.93
    榄
    0.93
     فونبیټ
    0.91
    ানন্দ
    0.91
    Act Density 0.003%

    No Known Activations