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

    Neuronpedia

    INDEX
    Explanations

    At

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manager
    -0.07
     Buster
    -0.07
    Manager
    -0.07
     VMware
    -0.06
    _timeout
    -0.06
    meler
    -0.06
    cision
    -0.06
    ORE
    -0.06
    	
↵
    -0.06
    ')}}">↵
    -0.06
    POSITIVE LOGITS
     äl
    0.07
    %@
    0.06
    所有
    0.06
    角
    0.06
     blok
    0.06
    Traffic
    0.06
     باشد
    0.06
     Magnet
    0.06
    <Article
    0.06
    =batch
    0.06
    Act Density 0.003%

    No Known Activations