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

    Neuronpedia

    INDEX
    Explanations

    ballot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reign
    -0.08
     Virt
    -0.07
    OMEM
    -0.07
    VEST
    -0.07
     vẫn
    -0.07
    udson
    -0.07
    Admin
    -0.07
    מוזיאון
    -0.07
     urging
    -0.07
    開發
    -0.07
    POSITIVE LOGITS
    ]{
    0.07
     casualty
    0.06
     ballots
    0.06
     Strauss
    0.06
    "]).
    0.06
    请注意
    0.06
     Ба
    0.06
    candidate
    0.06
    Instances
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations