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

    Neuronpedia

    INDEX
    Explanations

    behind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seven
    -0.06
     Cry
    -0.06
     blah
    -0.06
     used
    -0.06
     Coronavirus
    -0.06
     etc
    -0.06
     cases
    -0.06
     scram
    -0.06
    =@"
    -0.06
     booked
    -0.06
    POSITIVE LOGITS
    羊
    0.07
     suspected
    0.07
    reator
    0.06
    .Ch
    0.06
     наблю
    0.06
    θερ
    0.06
    Recipe
    0.06
    logs
    0.06
    Tracker
    0.06
     nghiên
    0.06
    Act Density 0.012%

    No Known Activations