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

    Neuronpedia

    INDEX
    Explanations

    First-person writing

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to uppercase acronyms or initialisms (e.g. “BEE”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    elp
    -0.07
    eron
    -0.06
     아래
    -0.06
     slated
    -0.06
     worsh
    -0.06
     lyon
    -0.06
    poon
    -0.06
     defective
    -0.05
     combin
    -0.05
    ryfall
    -0.05
    POSITIVE LOGITS
     kry
    0.07
    	anim
    0.07
    γγραφ
    0.06
     zih
    0.06
    (chunk
    0.06
    [opt
    0.06
    SessionFactory
    0.06
    liğine
    0.06
    _ios
    0.06
    ้าย
    0.06
    Act Density 0.099%

    No Known Activations