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

    Neuronpedia

    INDEX
    Explanations

    quoting when citing sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    撓
    -1.65
    ☫
    -1.59
        
    -1.58
    ernalia
    -1.57
    也没
    -1.56
          
    -1.55
    jestel
    -1.52
    焢
    -1.52
    риста
    -1.52
    ”)
    -1.52
    POSITIVE LOGITS
     the
    2.48
     bezw
    2.00
    atser
    1.93
    ݯ
    1.80
    guigu
    1.75
     OGSÅ
    1.71
    genodigd
    1.71
     Він
    1.69
    után
    1.68
     involucra
    1.67
    Act Density 0.012%

    No Known Activations