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

    Neuronpedia

    INDEX
    Explanations

    patents

    np_max-act · gemini-2.0-flash

    This neuron detects references to patent publications (e.g. “Japanese Laid-Open Patent Publication No.” and its document numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    اطل
    -0.07
     độc
    -0.07
     Fence
    -0.07
     Saras
    -0.07
    atrice
    -0.06
    ushort
    -0.06
     Brick
    -0.06
    asına
    -0.06
    strar
    -0.06
    iddi
    -0.06
    POSITIVE LOGITS
    یمی
    0.06
                                    
    0.06
     sci
    0.06
     […]...↵
    0.06
     Procedures
    0.06
     trimmed
    0.05
    ¦
    0.05
    ほど
    0.05
    .PropTypes
    0.05
    	seq
    0.05
    Act Density 0.000%

    No Known Activations