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

    Neuronpedia

    INDEX
    Explanations

    Time durations

    np_max-act · gemini-2.0-flash

    The neuron specializes in detecting numerical expressions (e.g. concentrations, times, and other measured values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    $a
    -0.06
    cctor
    -0.06
     devs
    -0.06
     acompanh
    -0.06
     �
    -0.06
     Killing
    -0.06
    ulled
    -0.06
     ys
    -0.06
    _even
    -0.05
    ;|
    -0.05
    POSITIVE LOGITS
     Vit
    0.07
     Seek
    0.06
    (getContext
    0.06
     پاورپوینت
    0.06
     savoir
    0.06
    hyp
    0.06
    .Convert
    0.06
     Barclays
    0.06
    	find
    0.06
    .getProperties
    0.06
    Act Density 0.037%

    No Known Activations