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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .mutex
    -0.06
    .Counter
    -0.06
    "We
    -0.06
    -Б
    -0.06
    Platforms
    -0.06
     LED
    -0.06
    -expanded
    -0.06
    25
    -0.06
     Languages
    -0.06
     sharply
    -0.06
    POSITIVE LOGITS
     interpretation
    0.07
     assail
    0.07
    ()>
    0.06
    恋
    0.06
     هنگام
    0.06
    liğinde
    0.06
    ние
    0.06
    _parts
    0.06
     disillusion
    0.06
     linebacker
    0.06
    Act Density 0.053%

    No Known Activations