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

    Neuronpedia

    INDEX
    Explanations

    links and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aop
    0.22
    .,"
    0.21
    лася
    0.21
     jez
    0.20
     revitalize
    0.20
    PSY
    0.20
    })"
    0.20
     eventful
    0.19
     revive
    0.19
    时间的
    0.19
    POSITIVE LOGITS
     quieras
    0.22
    beeld
    0.21
    mathbf
    0.21
     दिल्ली
    0.20
    इसी
    0.20
     görül
    0.19
     de
    0.19
    agner
    0.19
    难
    0.19
     इसी
    0.19
    Act Density 0.004%

    No Known Activations