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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쨩
    -0.07
    reflection
    -0.07
    ﭔ
    -0.07
    yyvsp
    -0.07
     ofApp
    -0.07
     elő
    -0.07
    캬
    -0.07
    婠
    -0.07
    .Offset
    -0.06
    OperationException
    -0.06
    POSITIVE LOGITS
    稳步推进
    0.08
    天鹅
    0.07
    所述
    0.07
    !(
    0.07
    .values
    0.07
    热潮
    0.07
    无缝
    0.06
    (',',$
    0.06
    selection
    0.06
    贯通
    0.06
    Act Density 0.002%

    No Known Activations