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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Matthias
    -0.07
     Surface
    -0.06
    倫
    -0.06
    rende
    -0.06
    implements
    -0.06
    .scene
    -0.06
    Mus
    -0.06
    Para
    -0.06
    rezent
    -0.06
     الإ
    -0.06
    POSITIVE LOGITS
    `↵
    0.06
    .Delay
    0.06
    -appointed
    0.06
    sofar
    0.06
    radient
    0.06
    ertz
    0.06
     части
    0.06
    (body
    0.06
     diferencia
    0.06
     dug
    0.06
    Act Density 0.008%

    No Known Activations