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

    Neuronpedia

    INDEX
    Explanations

    code executions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Friends
    -0.07
    md
    -0.07
    uesday
    -0.06
     How
    -0.06
    eson
    -0.06
    G
    -0.06
    。我
    -0.06
    	Config
    -0.06
     feed
    -0.06
    dance
    -0.06
    POSITIVE LOGITS
     Deferred
    0.07
     висок
    0.06
    дах
    0.06
    extend
    0.06
    988
    0.06
    приклад
    0.06
     LocalDateTime
    0.06
    <Cell
    0.06
    "),"
    0.06
    .DateTimeField
    0.06
    Act Density 0.036%

    No Known Activations