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

    Neuronpedia

    INDEX
    Explanations

    attribute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rod
    -0.07
     Dome
    -0.06
    .Mobile
    -0.06
    Rod
    -0.06
     Drop
    -0.06
     menn
    -0.06
     flash
    -0.06
     Ideas
    -0.06
     Fed
    -0.06
     مثبت
    -0.06
    POSITIVE LOGITS
    -one
    0.07
    /*!
    0.07
    ồng
    0.07
    ुट
    0.07
     складі
    0.07
    adaptive
    0.07
    @"
    0.06
     failures
    0.06
    اجر
    0.06
    лаз
    0.06
    Act Density 0.005%

    No Known Activations