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

    Neuronpedia

    INDEX
    Explanations

    Legal career

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     certificates
    -0.06
     Re
    -0.06
     breeds
    -0.06
     integr
    -0.06
     Us
    -0.06
     Chairs
    -0.06
     πά
    -0.06
     nob
    -0.06
    릭
    -0.06
     soud
    -0.06
    POSITIVE LOGITS
    acio
    0.06
    leon
    0.06
    ylül
    0.06
     hogy
    0.06
    localStorage
    0.06
     plur
    0.06
    kubectl
    0.06
    лого
    0.06
    (Seq
    0.06
    wen
    0.06
    Act Density 0.020%

    No Known Activations