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

    Neuronpedia

    INDEX
    Explanations

    increasingly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пло
    -0.08
    \Tests
    -0.07
    मक
    -0.07
     Hospital
    -0.07
     idiots
    -0.07
     Cups
    -0.07
     plagiar
    -0.07
     thrott
    -0.07
     Souls
    -0.07
     Sep
    -0.07
    POSITIVE LOGITS
     increasingly
    0.14
     aşırı
    0.07
    不断
    0.07
    ，最
    0.06
     kesinlikle
    0.06
    redi
    0.06
    (Common
    0.06
     Loader
    0.06
    ，更
    0.06
     často
    0.06
    Act Density 0.011%

    No Known Activations