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

    Neuronpedia

    INDEX
    Explanations

    Scalar fields (phi)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     destroyer
    -0.07
    クリ
    -0.06
    _sta
    -0.06
    调
    -0.06
    umerator
    -0.06
     needle
    -0.06
    ian
    -0.06
    _Draw
    -0.06
     segu
    -0.06
    要求
    -0.06
    POSITIVE LOGITS
    /LICENSE
    0.06
    ΙΤ
    0.06
    HOST
    0.06
    REGISTER
    0.06
     первой
    0.06
     cosmetic
    0.06
    ICK
    0.06
    [M
    0.06
     opc
    0.06
     الأس
    0.05
    Act Density 0.004%

    No Known Activations