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

    Neuronpedia

    INDEX
    Explanations

    at a glance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    0.70
     Shout
    0.68
     on
    0.67
     or
    0.66
     Million
    0.57
     yardım
    0.57
     Aleks
    0.56
     anniversary
    0.55
     curling
    0.55
     shout
    0.54
    POSITIVE LOGITS
    stdio
    0.64
    lež
    0.62
    auj
    0.61
     ток
    0.59
     СК
    0.58
    fromi
    0.58
    unsafe
    0.57
    कृतिक
    0.57
    pK
    0.55
    かっこ
    0.55
    Act Density 0.001%

    No Known Activations