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

    Neuronpedia

    INDEX
    Explanations

    Code/database queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ρ
    -0.07
     charg
    -0.06
    (SQL
    -0.06
    анти
    -0.06
    ial
    -0.06
     FOUR
    -0.06
     rail
    -0.06
    ials
    -0.06
     room
    -0.06
    Global
    -0.06
    POSITIVE LOGITS
    eket
    0.07
    ınma
    0.06
     MouseEvent
    0.06
     converts
    0.06
     jsonify
    0.06
     Malaysian
    0.06
    ева
    0.06
    FromFile
    0.06
     erase
    0.06
    _spot
    0.06
    Act Density 0.003%

    No Known Activations