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

    Neuronpedia

    INDEX
    Explanations

    scientific results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mag
    -0.07
    -treated
    -0.06
     чувств
    -0.06
     steak
    -0.06
    �
    -0.06
     citrus
    -0.06
    _conversion
    -0.06
    교
    -0.06
     cabinets
    -0.06
     mice
    -0.06
    POSITIVE LOGITS
     actionTypes
    0.07
    าผ
    0.06
     """
↵
↵
    0.06
    eyed
    0.06
     동
    0.06
    pages
    0.06
    riendly
    0.06
     اض
    0.06
     BİR
    0.06
     wrest
    0.06
    Act Density 0.065%

    No Known Activations