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

    Neuronpedia

    INDEX
    Explanations

    Fab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ии
    -0.07
    ins
    -0.07
    興
    -0.07
     tão
    -0.06
    ína
    -0.06
    _Post
    -0.06
     chiefly
    -0.06
    орту
    -0.06
    _Out
    -0.06
     mosquitoes
    -0.06
    POSITIVE LOGITS
     persist
    0.07
    limitations
    0.07
    _COMPAT
    0.07
     المدر
    0.06
     checkout
    0.06
     limitations
    0.06
     Difference
    0.06
     zm
    0.06
     usb
    0.06
     patches
    0.06
    Act Density 0.003%

    No Known Activations