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

    Neuronpedia

    INDEX
    Explanations

    language confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     выгляд
    0.38
     njihov
    0.37
    ściej
    0.37
     jeweiligen
    0.35
     niiden
    0.35
    拓展
    0.34
    ொட
    0.34
     аспек
    0.34
    след
    0.34
     невероят
    0.34
    POSITIVE LOGITS
     ​​
    0.42
     auspicious
    0.38
     Russian
    0.37
     XNUMX
    0.37
     Brownian
    0.34
     Yoruba
    0.33
     salvation
    0.33
     urbanization
    0.33
     Ayurveda
    0.33
     cacao
    0.32
    Act Density 0.053%

    No Known Activations