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

    Neuronpedia

    INDEX
    Explanations

    features and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    情节
    0.80
     방법
    0.78
     działalności
    0.76
     rainbows
    0.76
     existencia
    0.75
    道具
    0.75
    新手
    0.74
     방법에
    0.73
    \%$
    0.72
    wicklung
    0.72
    POSITIVE LOGITS
     utilizes
    1.30
     utilizing
    1.18
    Featuring
    1.10
     Utilizing
    1.09
     utilize
    1.09
     featuring
    1.08
     utilising
    1.08
     sporting
    1.05
     utilises
    1.05
     boasting
    1.04
    Act Density 0.813%

    No Known Activations