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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chains
    -0.06
    Dur
    -0.06
     ва
    -0.06
    groupon
    -0.06
     coco
    -0.06
     Dur
    -0.06
    (itemId
    -0.06
     Ко
    -0.06
     Gael
    -0.06
     вона
    -0.06
    POSITIVE LOGITS
     Heavy
    0.07
     replaces
    0.07
     luxury
    0.07
     ofstream
    0.07
    channel
    0.06
     terrorists
    0.06
    "",↵
    0.06
     ")"↵
    0.06
    ifstream
    0.06
     urban
    0.06
    Act Density 0.003%

    No Known Activations