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

    Neuronpedia

    INDEX
    Explanations

    York

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Queens
    -0.69
     Flushing
    -0.69
     queens
    -0.68
     Kasper
    -0.66
     KINGS
    -0.63
     juniors
    -0.60
     Kings
    -0.59
     Kamil
    -0.59
     Borough
    -0.59
     QUE
    -0.56
    POSITIVE LOGITS
     utafitiHapana
    0.54
    ContentAsync
    0.51
    الحياه
    0.50
    }]{
    0.50
    PRNewswire
    0.49
    HasForeignKey
    0.47
     useAppContext
    0.47
    ModelSerializer
    0.46
    abstractmethod
    0.45
    awtextra
    0.44
    Act Density 0.001%

    No Known Activations