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

    Neuronpedia

    INDEX
    Explanations

    Technical/scientific documents

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions that site rules or the scope of a question have changed.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Swarm
    -0.07
     shoulders
    -0.07
    823
    -0.06
    sounds
    -0.06
     loans
    -0.06
     skulls
    -0.06
    113
    -0.06
     chest
    -0.06
     رسانه
    -0.06
     arenas
    -0.06
    POSITIVE LOGITS
    amanho
    0.06
    <=
    0.06
    --------------
    0.06
    (木
    0.06
    (Base
    0.06
    relude
    0.06
    (Collection
    0.06
    COMMENT
    0.06
    _EDGE
    0.06
    _IMP
    0.06
    Act Density 0.394%

    No Known Activations