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

    Neuronpedia

    INDEX
    Explanations

    summarize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eight
    -0.06
    хід
    -0.06
     Fel
    -0.06
    Fish
    -0.06
    Ten
    -0.06
    Atual
    -0.06
    aravel
    -0.06
     kneeling
    -0.06
     เพราะ
    -0.06
    ocial
    -0.06
    POSITIVE LOGITS
     summarize
    0.10
     summary
    0.08
     summar
    0.08
     Murphy
    0.07
     Summers
    0.07
    .Measure
    0.07
    .jsoup
    0.07
    ,tmp
    0.07
     Winston
    0.07
     NU
    0.07
    Act Density 0.040%

    No Known Activations