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

    Neuronpedia

    INDEX
    Explanations

    half

    np_max-act · gemini-2.0-flash

    The neuron never fires—i.e. it’s essentially “dead” and does not respond to any token patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ствует
    -0.06
     иде
    -0.06
     �
    -0.06
    myp
    -0.06
     opportunities
    -0.06
    uuml
    -0.06
     Levin
    -0.06
     fld
    -0.06
     �
    -0.06
    )')↵
    -0.06
    POSITIVE LOGITS
     dễ
    0.07
    	find
    0.07
    ctica
    0.07
    _BLUE
    0.06
     podporu
    0.06
    ~
    0.06
     Argentine
    0.06
     Seah
    0.06
     مادر
    0.06
     Controllers
    0.06
    Act Density 0.013%

    No Known Activations