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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    อาหาร
    -0.07
     PERF
    -0.06
    (inter
    -0.06
    ROUND
    -0.06
     cushions
    -0.06
    osas
    -0.06
    _FEED
    -0.06
    quot
    -0.06
    _friends
    -0.06
     PLAYER
    -0.06
    POSITIVE LOGITS
    \Extension
    0.07
     reasonable
    0.06
     Aer
    0.06
    .ins
    0.06
    ώνα
    0.06
     باشگاه
    0.06
     correspondence
    0.06
    	group
    0.06
     resembl
    0.06
     intention
    0.06
    Act Density 0.033%

    No Known Activations