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

    Neuronpedia

    INDEX
    Explanations

    ok

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     examples
    -0.08
     sempre
    -0.06
    ايي
    -0.06
    登
    -0.06
     citing
    -0.06
     VM
    -0.06
    larının
    -0.06
     Believe
    -0.06
     сопров
    -0.06
     minh
    -0.06
    POSITIVE LOGITS
     Ultimate
    0.07
     toler
    0.07
     errorMessage
    0.07
    :view
    0.06
    utch
    0.06
    ales
    0.06
     shifting
    0.06
     مدر
    0.06
     Irish
    0.06
     glob
    0.06
    Act Density 0.017%

    No Known Activations