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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens, picking out numbers and numerical values (e.g., digits and decimals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    |-
    -0.07
    Pizza
    -0.07
    Short
    -0.07
    anchise
    -0.07
    -Jan
    -0.07
    	background
    -0.07
     Jana
    -0.06
    .First
    -0.06
     meat
    -0.06
    _root
    -0.06
    POSITIVE LOGITS
    海道
    0.06
    ợ
    0.06
     дж
    0.06
    Cİ
    0.06
    ؟
    0.05
    ，却
    0.05
     �
    0.05
    .styles
    0.05
    olicitud
    0.05
    utenberg
    0.05
    Act Density 0.038%

    No Known Activations