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

    Neuronpedia

    INDEX
    Explanations

    happiness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consequences
    -0.06
     pumping
    -0.06
    ’ya
    -0.06
    忽
    -0.06
     drop
    -0.06
    ф
    -0.06
    Expect
    -0.06
    -filled
    -0.06
     cold
    -0.06
     vastly
    -0.05
    POSITIVE LOGITS
    .Rec
    0.08
     validar
    0.07
    _contents
    0.06
     PrintWriter
    0.06
    dür
    0.06
     surrounds
    0.06
     jedis
    0.06
    .Car
    0.06
    UNICATION
    0.06
    <|python_tag|>
    0.06
    Act Density 0.051%

    No Known Activations