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

    Neuronpedia

    INDEX
    Explanations

    a and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Comput
    -0.08
    �
    -0.07
     attacks
    -0.07
     Wag
    -0.06
    ornings
    -0.06
    lots
    -0.06
    Trading
    -0.06
     Wid
    -0.06
     Laboratories
    -0.06
     Cob
    -0.06
    POSITIVE LOGITS
    ysical
    0.07
     сом
    0.06
    ügen
    0.06
    yclerView
    0.06
     sai
    0.06
     têm
    0.06
    .seek
    0.06
    *m
    0.06
    (amount
    0.06
    metry
    0.06
    Act Density 0.013%

    No Known Activations