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
     Bacon
    -0.08
    .guid
    -0.07
     sail
    -0.06
    עץ
    -0.06
    ᛐ
    -0.06
     Licensed
    -0.06
    Ỡ
    -0.06
    层面
    -0.06
    igham
    -0.06
    全方位
    -0.06
    POSITIVE LOGITS
     .*
    0.07
     branching
    0.07
     تعتبر
    0.07
    すごく
    0.07
     invoking
    0.07
     désir
    0.07
     mixing
    0.07
     objections
    0.06
    严重影响
    0.06
     ik
    0.06
    Act Density 0.001%

    No Known Activations