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

    Neuronpedia

    INDEX
    Explanations

    technical or explanatory contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Depression
    0.28
     rebels
    0.26
     Greece
    0.26
     museums
    0.26
     historian
    0.26
     articulate
    0.26
     Ayurveda
    0.26
     Mussolini
    0.26
     revolutionaries
    0.26
     ascertained
    0.25
    POSITIVE LOGITS
    )|
    0.48
    是的
    0.31
    洍
    0.29
     fclose
    0.29
    办
    0.29
    呕
    0.28
    বুধবার
    0.28
     除
    0.28
    季度
    0.27
     ಏ
    0.27
    Act Density 0.189%

    No Known Activations