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

    Neuronpedia

    INDEX
    Explanations

    code formatting with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etkinlik
    0.37
    ইন্দ
    0.36
    webstore
    0.36
     weld
    0.34
     Shelton
    0.33
     recreate
    0.33
    ەد
    0.33
     saja
    0.32
     launchers
    0.32
     வால்பேப்பர்கள்
    0.32
    POSITIVE LOGITS
     तीसरे
    0.40
     기
    0.33
    ódio
    0.31
    른
    0.31
     teen
    0.30
    びっくり
    0.30
     चौथे
    0.30
    Lastly
    0.30
    bic
    0.29
    เก
    0.29
    Act Density 0.072%

    No Known Activations