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

    Neuronpedia

    INDEX
    Explanations

    16S, scanner, Degrees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.92
     shake
    0.76
     detergent
    0.72
     guard
    0.71
     Athena
    0.70
     (
    0.69
     champion
    0.68
     steering
    0.67
     disp
    0.67
     dy
    0.66
    POSITIVE LOGITS
    ⃣
    1.07
     градусов
    1.06
    speeds
    1.04
     минут
    1.00
    ️⃣
    0.99
     spezielle
    0.96
     Degrees
    0.95
    㤈
    0.94
    sentation
    0.92
    GRESS
    0.90
    Act Density 0.276%

    No Known Activations