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

    Neuronpedia

    INDEX
    Explanations

    gap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hav
    -0.07
    'aut
    -0.07
     assaults
    -0.07
    χη
    -0.07
     Fauc
    -0.06
     READ
    -0.06
    .sam
    -0.06
     relational
    -0.06
     goo
    -0.06
    _skip
    -0.06
    POSITIVE LOGITS
     Исп
    0.06
     ignor
    0.06
     bookmarks
    0.06
    .URL
    0.06
    就是
    0.06
    -products
    0.06
    upport
    0.06
    using
    0.06
     中国
    0.06
     marginLeft
    0.06
    Act Density 0.016%

    No Known Activations