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

    Neuronpedia

    INDEX
    Explanations

    current

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    badge
    -0.07
     taxing
    -0.06
     enclosing
    -0.06
     DBG
    -0.06
    ene
    -0.06
     بإ
    -0.06
     biases
    -0.06
    wiąz
    -0.06
     Cree
    -0.06
    targets
    -0.06
    POSITIVE LOGITS
     DialogResult
    0.07
    ươi
    0.07
     kterých
    0.06
     вихов
    0.06
    ”.↵↵
    0.06
    监听页面
    0.06
    Paragraph
    0.06
     María
    0.06
    blings
    0.06
    створ
    0.06
    Act Density 0.000%

    No Known Activations