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

    Neuronpedia

    INDEX
    Explanations

    sexual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     రైతు
    0.81
     Einstein
    0.75
     RMSE
    0.75
     IComparable
    0.74
    嵌入
    0.73
     stopwords
    0.73
     microcontroller
    0.72
     Evernote
    0.71
    ICEF
    0.69
     انصاف
    0.69
    POSITIVE LOGITS
     sexual
    3.50
     sexually
    3.12
     Sexual
    3.01
    Sexual
    3.00
     erotic
    2.97
     sexuality
    2.93
     sex
    2.79
    sexual
    2.70
     seksual
    2.65
     sensual
    2.58
    Act Density 2.255%

    No Known Activations