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

    Neuronpedia

    INDEX
    Explanations

    lists and coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skill
    -0.07
    spaces
    -0.07
    Address
    -0.06
     Henderson
    -0.06
     washed
    -0.06
    ("/
    -0.06
     UK
    -0.06
     Roll
    -0.06
     ख
    -0.06
    .direct
    -0.06
    POSITIVE LOGITS
     خدمات
    0.07
     inclination
    0.07
    ende
    0.07
    CellValue
    0.06
     peso
    0.06
    üsseldorf
    0.06
    athom
    0.06
    #ae
    0.06
    _probs
    0.06
     Goku
    0.06
    Act Density 0.011%

    No Known Activations