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

    Neuronpedia

    INDEX
    Explanations

    News reporting

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens and numeric expressions (years, counts, percentages, monetary amounts, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Applied
    -0.06
    GLenum
    -0.06
     nickname
    -0.06
     اجرای
    -0.06
    gd
    -0.06
    ินค
    -0.06
    Beth
    -0.06
     Business
    -0.06
     Beth
    -0.06
    Discount
    -0.06
    POSITIVE LOGITS
    +',
    0.07
    .BO
    0.06
     Proposition
    0.06
     RHS
    0.06
     Shields
    0.06
    -opacity
    0.06
     vp
    0.06
    _RED
    0.06
    σα
    0.06
     Forge
    0.06
    Act Density 0.191%

    No Known Activations