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

    Neuronpedia

    INDEX
    Explanations

    experience

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fusion
    -0.07
     fak
    -0.06
    rights
    -0.06
     invaded
    -0.06
    Saved
    -0.06
    ルド
    -0.06
     Truth
    -0.06
     Hot
    -0.06
    iais
    -0.06
     wasted
    -0.05
    POSITIVE LOGITS
    eline
    0.09
     gratuito
    0.07
     mundane
    0.07
     khuyến
    0.07
     chứng
    0.07
     relacion
    0.07
     thước
    0.07
    (day
    0.07
    elu
    0.06
     matrimon
    0.06
    Act Density 0.019%

    No Known Activations