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
     piano
    -0.07
     conceivable
    -0.07
     который
    -0.06
     팬
    -0.06
    .stage
    -0.06
     playground
    -0.06
     Vader
    -0.06
    .Parser
    -0.06
     disorder
    -0.06
     chew
    -0.06
    POSITIVE LOGITS
     Products
    0.06
    FO
    0.06
    Archive
    0.06
    okes
    0.06
     худож
    0.06
    Purchase
    0.06
    Sk
    0.06
    BS
    0.06
    _THREADS
    0.06
    Ÿ
    0.06
    Act Density 0.000%

    No Known Activations