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

    Neuronpedia

    INDEX
    Explanations

    conditional situations

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens that convey universal generality or absoluteness (e.g., “any,” “what,” “every,” “no matter”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     systems
    -0.07
    _EXTERNAL
    -0.07
    (login
    -0.07
    -v
    -0.06
    Gro
    -0.06
    Notification
    -0.06
     system
    -0.06
    -extension
    -0.06
    Throw
    -0.06
     máy
    -0.06
    POSITIVE LOGITS
     Enums
    0.07
     vídeos
    0.07
    ilinx
    0.06
     Medal
    0.06
    .tem
    0.06
     Ninth
    0.06
     فت
    0.06
    (&_
    0.06
    _INCLUDED
    0.06
    semi
    0.06
    Act Density 0.007%

    No Known Activations