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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literals containing decimal points (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     uno
    -0.07
     Wolfe
    -0.06
    professional
    -0.06
    _patterns
    -0.06
    /qt
    -0.06
    (i
    -0.06
    (wrapper
    -0.06
    -network
    -0.06
    -react
    -0.06
     Dropbox
    -0.06
    POSITIVE LOGITS
     Regions
    0.07
    .channels
    0.06
     mt
    0.06
    imir
    0.06
     están
    0.06
    ічного
    0.06
     �
    0.06
    ـل
    0.06
    =row
    0.06
     سان
    0.06
    Act Density 0.076%

    No Known Activations