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

    Neuronpedia

    INDEX
    Explanations

    those

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transform
    -0.07
    OM
    -0.07
     clustering
    -0.06
    iom
    -0.06
     doctoral
    -0.06
    難
    -0.06
     aver
    -0.06
     فاصله
    -0.06
    773
    -0.06
    _should
    -0.06
    POSITIVE LOGITS
    Plug
    0.06
     acqu
    0.06
     accessible
    0.06
     susceptible
    0.06
    Cream
    0.06
     Nude
    0.06
    +s
    0.06
    sender
    0.06
     защ
    0.06
    iquement
    0.06
    Act Density 0.017%

    No Known Activations