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

    Neuronpedia

    INDEX
    Explanations

    python application program

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    soff
    0.66
     याचा
    0.65
    nehmens
    0.65
    اخ
    0.64
    ewer
    0.62
    とし
    0.61
     Faktor
    0.60
    utation
    0.59
     Abb
    0.59
     soi
    0.57
    POSITIVE LOGITS
     >=
    1.06
    生态
    1.01
     scripting
    1.00
    Script
    0.98
     Tutorial
    0.97
     Script
    0.96
    における
    0.94
     ≥
    0.94
    において
    0.93
     idioms
    0.92
    Act Density 0.473%

    No Known Activations