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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peaks
    -0.07
    亞
    -0.07
    anyl
    -0.06
    osopher
    -0.06
     VERSION
    -0.06
    CEPTION
    -0.06
     {?>↵
    -0.06
    #error
    -0.06
    rored
    -0.06
     gossip
    -0.06
    POSITIVE LOGITS
    istringstream
    0.07
    .Broadcast
    0.07
     çıkar
    0.07
    lobals
    0.07
    通常
    0.06
     '\
    0.06
    _On
    0.06
     hap
    0.06
    	cerr
    0.06
    ующий
    0.06
    Act Density 0.003%

    No Known Activations