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

    Neuronpedia

    INDEX
    Explanations

    Code snippets/technical content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.59
     intellectuelle
    -0.54
     DICE
    -0.47
     culturelles
    -0.46
     disparu
    -0.46
    seamnă
    -0.45
     Closer
    -0.45
     يتيمه
    -0.44
     spade
    -0.43
     Calling
    -0.43
    POSITIVE LOGITS
    chartInstance
    0.73
    UnusedPrivate
    0.68
    GEBURTSDATUM
    0.67
    verwijspagina
    0.63
    JspWriter
    0.62
    setVerticalGroup
    0.60
    ImageContext
    0.60
     endforeach
    0.59
    новниш
    0.59
     محفوظة
    0.59
    Act Density 0.001%

    No Known Activations