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

    Neuronpedia

    INDEX
    Explanations

    noise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rhyme
    -0.07
    等
    -0.07
     현
    -0.07
     lips
    -0.07
    绍
    -0.07
    .friend
    -0.07
    Pressure
    -0.06
    TP
    -0.06
    ictions
    -0.06
    text
    -0.06
    POSITIVE LOGITS
     Interested
    0.06
     LGPL
    0.06
    Swagger
    0.06
    Roboto
    0.06
    .Article
    0.06
    İSİ
    0.06
    bable
    0.06
    .temp
    0.06
     Sergio
    0.06
     süresi
    0.06
    Act Density 0.149%

    No Known Activations