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

    Neuronpedia

    INDEX
    Explanations

    technical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     specular
    -0.07
    lica
    -0.07
    Rx
    -0.06
    ridden
    -0.06
    ưa
    -0.06
    aln
    -0.06
    ibles
    -0.06
     döndü
    -0.06
    ترة
    -0.06
     땅
    -0.06
    POSITIVE LOGITS
     Item
    0.07
     One
    0.06
    [Unit
    0.06
     gentleman
    0.06
    <Account
    0.06
     Kurum
    0.06
    (bottom
    0.06
    職
    0.06
    One
    0.06
    	key
    0.06
    Act Density 0.000%

    No Known Activations