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

    Neuronpedia

    INDEX
    Explanations

    random text, code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sow
    -0.07
     functionName
    -0.06
     dom
    -0.06
     separating
    -0.06
    áhl
    -0.06
    joy
    -0.06
    jack
    -0.06
     COMPUT
    -0.06
    "When
    -0.06
     decorative
    -0.06
    POSITIVE LOGITS
     Talent
    0.07
    чук
    0.06
    Luckily
    0.06
    /alert
    0.06
     числе
    0.06
    Nuitka
    0.06
    去
    0.06
     sympathy
    0.06
    ，其
    0.06
    -nil
    0.06
    Act Density 0.002%

    No Known Activations