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

    Neuronpedia

    INDEX
    Explanations

    material properties

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric measurement tokens (numbers, decimal values, units) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     osoby
    -0.06
     tree
    -0.06
    _VERTICAL
    -0.06
    -day
    -0.06
     filter
    -0.06
     Elections
    -0.06
     dim
    -0.06
     drawers
    -0.06
     vagina
    -0.06
     quanh
    -0.06
    POSITIVE LOGITS
     '',
    0.06
     Дон
    0.06
    tems
    0.06
     talked
    0.06
    �
    0.06
    ड़क
    0.06
     Wit
    0.06
    ،
    0.06
    PI
    0.06
    .Authentication
    0.06
    Act Density 0.023%

    No Known Activations