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

    Neuronpedia

    INDEX
    Explanations

    /jquery

    np_max-act · gemini-2.0-flash

    The neuron fires on floating‐point numbers (i.e. tokens containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ủa
    -0.07
    Fine
    -0.07
    оятель
    -0.07
    أك
    -0.06
    _reviews
    -0.06
     Fore
    -0.06
     Schwe
    -0.06
     그래
    -0.06
    فته
    -0.06
    tracted
    -0.06
    POSITIVE LOGITS
     тяжел
    0.08
    $url
    0.07
    --[
    0.07
    併
    0.07
     calorie
    0.06
    DNA
    0.06
     treasurer
    0.06
    pdb
    0.06
    len
    0.06
     incumbent
    0.06
    Act Density 0.001%

    No Known Activations