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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OX
    -0.07
     vrát
    -0.07
    _tunnel
    -0.07
    .histogram
    -0.07
    .FLOAT
    -0.07
     observers
    -0.06
    Concern
    -0.06
     plumber
    -0.06
    DataRow
    -0.06
    "W
    -0.06
    POSITIVE LOGITS
    шие
    0.07
    _lite
    0.06
     χρή
    0.06
     egregious
    0.06
    gmail
    0.06
     ubiquitous
    0.06
     медицин
    0.06
     діяльності
    0.06
    cin
    0.05
     fruity
    0.05
    Act Density 0.075%

    No Known Activations