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

    Neuronpedia

    INDEX
    Explanations

    interference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Quantity
    -0.07
    *>&
    -0.07
     Yüz
    -0.07
     넣
    -0.07
    /my
    -0.07
    Imports
    -0.06
    .copy
    -0.06
    .month
    -0.06
     νο
    -0.06
     thế
    -0.06
    POSITIVE LOGITS
     درد
    0.07
    .Logic
    0.06
    minecraft
    0.06
     rhythms
    0.06
     bibli
    0.06
    ternal
    0.06
        ↵↵
    0.06
     OSD
    0.06
     anzeigen
    0.06
     IV
    0.06
    Act Density 0.004%

    No Known Activations