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

    Neuronpedia

    INDEX
    Explanations

    asterisks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (GUI
    -0.07
     camino
    -0.07
    =query
    -0.07
    707
    -0.07
     ACM
    -0.07
    boat
    -0.07
     Steps
    -0.06
     amis
    -0.06
     Woche
    -0.06
     April
    -0.06
    POSITIVE LOGITS
     Stake
    0.07
    レット
    0.06
     Сер
    0.06
     Essential
    0.06
    .customer
    0.06
     České
    0.06
    ffffff
    0.06
     "#{
    0.06
    Ca
    0.06
    .BorderSide
    0.06
    Act Density 0.012%

    No Known Activations