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

    Neuronpedia

    INDEX
    Explanations

    Politics/elections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ober
    -0.07
     напрям
    -0.07
    _Copy
    -0.06
     phòng
    -0.06
     usuario
    -0.06
     autor
    -0.06
     Bayesian
    -0.06
    _One
    -0.06
     Univers
    -0.06
     همین
    -0.06
    POSITIVE LOGITS
    distinct
    0.08
    mAh
    0.07
    _leave
    0.06
    )-
    0.06
     Mitgli
    0.06
     Hon
    0.06
    .Reflection
    0.06
     �
    0.06
    flatten
    0.06
    GOP
    0.06
    Act Density 0.261%

    No Known Activations