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

    Neuronpedia

    INDEX
    Explanations

    color codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Night
    -0.07
    =-=-=-=-
    -0.07
     night
    -0.07
     Bel
    -0.06
    _bw
    -0.06
    parts
    -0.06
    Ω
    -0.06
    보험
    -0.06
     nails
    -0.06
    cakes
    -0.06
    POSITIVE LOGITS
    Japanese
    0.07
     Основ
    0.07
     GeForce
    0.06
     explosive
    0.06
     french
    0.06
    Esp
    0.06
    GED
    0.06
     Pols
    0.06
     thriving
    0.06
     renewable
    0.06
    Act Density 0.008%

    No Known Activations