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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yas
    -0.07
     sa
    -0.06
    وپ
    -0.06
     naw
    -0.06
    روط
    -0.06
    _CONTROLLER
    -0.06
    ประโย
    -0.06
     дем
    -0.06
     helium
    -0.06
    wood
    -0.06
    POSITIVE LOGITS
     Attachment
    0.07
    较
    0.07
    Attachment
    0.06
    ()]
    0.06
    /DD
    0.06
    predicted
    0.06
         
    0.06
     Oasis
    0.06
    附
    0.06
    protected
    0.06
    Act Density 0.014%

    No Known Activations