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

    Neuronpedia

    INDEX
    Explanations

    Android code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Firearms
    -0.07
     deepen
    -0.07
    疑
    -0.07
     broadcasting
    -0.07
    isspace
    -0.07
    approve
    -0.06
     Preparation
    -0.06
    Evaluate
    -0.06
    伊朗
    -0.06
     Points
    -0.06
    POSITIVE LOGITS
     Конечно
    0.07
     constraints
    0.07
     culprit
    0.07
     العامة
    0.07
     мало
    0.07
    静态
    0.07
     zad
    0.07
    ugas
    0.07
    썽
    0.07
    给她
    0.07
    Act Density 0.001%

    No Known Activations