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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    梯
    -0.07
     زیب
    -0.07
    ixin
    -0.07
     اختل
    -0.07
     للت
    -0.06
     Deep
    -0.06
    assen
    -0.06
    ANGLES
    -0.06
    /cache
    -0.06
    POSITIVE LOGITS
     api
    0.08
     disappeared
    0.07
     academia
    0.07
    _working
    0.06
     Garrett
    0.06
     workplaces
    0.06
     messed
    0.06
    UICollectionView
    0.06
     interventions
    0.06
    (rest
    0.06
    Act Density 0.000%

    No Known Activations