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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the phrase “power of,” especially in headings or titles like “The Power of ….”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Hashtable
    -0.07
    622
    -0.06
    442
    -0.06
    -disc
    -0.06
    SV
    -0.06
     таблиц
    -0.06
    _chat
    -0.06
    рует
    -0.06
    -folder
    -0.06
    'email
    -0.06
    POSITIVE LOGITS
     profoundly
    0.06
     Absolutely
    0.06
     Twins
    0.06
     �
    0.06
     powerhouse
    0.06
    -agent
    0.06
    ентом
    0.06
     Riding
    0.06
    aming
    0.06
    _density
    0.06
    Act Density 0.016%

    No Known Activations