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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash

    The neuron detects floating-point numeric tokens (e.g. version‐style decimal numbers) in license header comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    reu
    -0.07
     Florian
    -0.07
     kısmı
    -0.06
    ько
    -0.06
    kinci
    -0.06
    ABCDE
    -0.06
     통
    -0.06
     CES
    -0.06
     uměl
    -0.06
    hec
    -0.06
    POSITIVE LOGITS
    -stack
    0.06
    conj
    0.06
    	throw
    0.06
     begs
    0.06
    ENDER
    0.06
     USDA
    0.06
    (END
    0.06
     interacting
    0.06
    _rem
    0.06
     بع
    0.06
    Act Density 0.000%

    No Known Activations