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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    但也
    -0.08
    division
    -0.07
    也會
    -0.07
    .createObject
    -0.07
     reality
    -0.07
    Dialog
    -0.07
     smoothly
    -0.07
    虾
    -0.07
    .dx
    -0.06
    ического
    -0.06
    POSITIVE LOGITS
     Sevent
    0.09
    增多
    0.08
     pard
    0.08
    ='%
    0.07
     pcap
    0.07
    ília
    0.07
     operand
    0.07
    Neill
    0.07
    があり
    0.07
    认为
    0.07
    Act Density 0.009%

    No Known Activations