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

    Neuronpedia

    INDEX
    Explanations

    Quotations/conversational

    np_max-act · gemini-2.0-flash

    This neuron is triggered by numeric tokens, especially decimal (floating-point) numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ft
    -0.06
    inar
    -0.06
    37
    -0.06
     Dev
    -0.06
    .“
    -0.06
     Νο
    -0.06
    meli
    -0.06
    18
    -0.06
    016
    -0.06
     Dolphin
    -0.06
    POSITIVE LOGITS
    กระ
    0.07
     deux
    0.06
     Toys
    0.06
     zaj
    0.06
    (items
    0.06
    cessive
    0.06
    .Resources
    0.06
    .todo
    0.06
    Pixel
    0.06
    .qt
    0.06
    Act Density 0.184%

    No Known Activations