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

    Neuronpedia

    INDEX
    Explanations

    ~

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;</
    -0.07
    .usage
    -0.07
    "];
    -0.07
     bearer
    -0.07
     affid
    -0.07
     buckets
    -0.07
     Barg
    -0.07
    }'",
    -0.07
     cards
    -0.07
     branching
    -0.07
    POSITIVE LOGITS
    met
    0.07
     ~
    0.07
    み
    0.07
     TELE
    0.07
     così
    0.07
    τηση
    0.07
    ту
    0.07
    hot
    0.07
    μα
    0.07
     despre
    0.06
    Act Density 0.015%

    No Known Activations