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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens (numbers and numeric constants) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    南
    -0.07
    opro
    -0.07
    ีต
    -0.06
    .progress
    -0.06
    чної
    -0.06
    出售
    -0.06
     нет
    -0.06
     subtract
    -0.06
     hakk
    -0.06
    сылки
    -0.06
    POSITIVE LOGITS
    (valor
    0.07
    Accessibility
    0.07
    Fal
    0.06
     bk
    0.06
     UserModel
    0.06
     loadImage
    0.06
     přím
    0.06
     BaseType
    0.06
    .JTable
    0.06
    _links
    0.06
    Act Density 0.008%

    No Known Activations