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

    Neuronpedia

    INDEX
    Explanations

    titles of books, music, etc

    oai_token-act-pair · gemini-2.0-flash

    Written works

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     res
    -0.60
     pen
    -0.49
     tra
    -0.47
     fal
    -0.46
     cref
    -0.46
     hon
    -0.45
    sp
    -0.45
     er
    -0.45
     te
    -0.44
     rat
    -0.44
    POSITIVE LOGITS
     ujednoznacz
    0.90
     intptr
    0.82
    DockStyle
    0.82
     femininas
    0.79
    NewUrlParser
    0.77
    UnsafeEnabled
    0.77
    fromnode
    0.77
     المعيارى
    0.76
     виправивши
    0.75
     '\\;'
    0.72
    Act Density 4.104%

    No Known Activations