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

    Neuronpedia

    INDEX
    Explanations

    Special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     управления
    -0.07
    ковод
    -0.07
    losed
    -0.07
    ją
    -0.07
     vaccination
    -0.07
     fian
    -0.06
     Row
    -0.06
     existing
    -0.06
     мел
    -0.06
     Vulcan
    -0.06
    POSITIVE LOGITS
    .SizeF
    0.06
    nání
    0.06
    _route
    0.06
     sendData
    0.06
    corlib
    0.06
     gerçekten
    0.06
    chrome
    0.06
     podle
    0.06
    }.${
    0.06
    モデル
    0.06
    Act Density 0.008%

    No Known Activations