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

    Neuronpedia

    INDEX
    Explanations

    Series 65 License

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Suerte
    -1.15
     specifik
    -1.14
    Şi
    -1.07
     насеље
    -1.06
     kabát
    -1.06
    τής
    -1.05
     سپس
    -1.05
     fortsatt
    -1.04
    вший
    -1.02
     technik
    -1.01
    POSITIVE LOGITS
     простой
    0.98
     рекомендуется
    0.96
    并
    0.94
    o
    0.93
    Go
    0.92
    `
    0.92
    ´
    0.88
     aktivieren
    0.86
    em
    0.85
    ?
    0.85
    Act Density 0.056%

    No Known Activations