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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivid
    -0.08
     kõ
    -0.08
     knj
    -0.08
     पुस्तक
    -0.08
     xov
    -0.08
    ева
    -0.08
     પુસ્તક
    -0.08
     TOD
    -0.07
     methane
    -0.07
     кел
    -0.07
    POSITIVE LOGITS
     further
    0.08
    Further
    0.08
    レス
    0.08
    さらに
    0.08
     incess
    0.07
    /',
    0.07
    -root
    0.07
     restore
    0.07
    Another
    0.07
    airs
    0.07
    Act Density 0.060%

    No Known Activations