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

    Neuronpedia

    INDEX
    Explanations

    Equivalence/rephrasing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     robotic
    -0.07
    하게
    -0.07
     acquisition
    -0.07
     mount
    -0.06
     transitions
    -0.06
    _ur
    -0.06
    -U
    -0.06
     SCR
    -0.06
    ुट
    -0.06
     chat
    -0.06
    POSITIVE LOGITS
    .lat
    0.07
     클래스
    0.06
    197
    0.06
    gerald
    0.06
     TASK
    0.06
     فرمان
    0.06
     genera
    0.06
     temperament
    0.06
    mpl
    0.06
     ｌ
    0.06
    Act Density 0.017%

    No Known Activations