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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical sets, particularly those involving the integers or other numerical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ${\mathbb{Z}}$ notation with superscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وتسجيلات
    -0.61
     kasarigan
    -0.61
    RegressionTest
    -0.59
    CDCl
    -0.55
    -0.55
    -0.52
    IVEREF
    -0.52
    FXML
    -0.50
    氘
    -0.50
     DirectX
    -0.50
    POSITIVE LOGITS
     paja
    0.42
    rfloor
    0.40
     prisión
    0.36
     ladrillo
    0.36
     selv
    0.34
    randint
    0.34
     habitudes
    0.34
     corazones
    0.33
     fabricación
    0.32
    навли
    0.32
    Act Density 0.030%

    No Known Activations