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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sans
    -0.08
    Comparator
    -0.07
    传奇
    -0.07
     Üç
    -0.06
     amateurs
    -0.06
    IPS
    -0.06
    /button
    -0.06
    urga
    -0.06
     Tutorial
    -0.06
     scal
    -0.06
    POSITIVE LOGITS
    <body
    0.07
     explores
    0.06
    анія
    0.06
     از
    0.06
    ناء
    0.06
    .thumbnail
    0.06
     akıl
    0.06
     oscillator
    0.06
    iology
    0.06
     :'
    0.06
    Act Density 0.019%

    No Known Activations