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

    Neuronpedia

    INDEX
    Explanations

    sailors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .epam
    -0.07
    apeut
    -0.07
     πως
    -0.06
     holiday
    -0.06
    .Constant
    -0.06
     تشخیص
    -0.06
    Including
    -0.06
     (=
    -0.06
     testcase
    -0.06
     Piano
    -0.06
    POSITIVE LOGITS
     sailors
    0.07
    .enter
    0.07
     sailor
    0.07
     تحقیق
    0.06
     Werner
    0.06
    (sorted
    0.06
     filenames
    0.06
    ierz
    0.06
    ışman
    0.06
     o
    0.06
    Act Density 0.010%

    No Known Activations