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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals (especially floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     TF
    -0.07
    .print
    -0.07
     Against
    -0.07
     poetic
    -0.06
    ary
    -0.06
     icy
    -0.06
     iOS
    -0.06
     Ernest
    -0.06
     giant
    -0.06
    _npc
    -0.06
    POSITIVE LOGITS
     Бі
    0.07
     gorge
    0.07
    signed
    0.07
     telecom
    0.06
    formData
    0.06
    ?>">
↵
    0.06
    کاران
    0.06
    =\""
    0.06
     »↵
    0.06
    (BigInteger
    0.06
    Act Density 0.001%

    No Known Activations