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

    Neuronpedia

    INDEX
    Explanations

    future

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Radar
    -0.07
    aco
    -0.07
     factorial
    -0.06
    277
    -0.06
    ारण
    -0.06
     ederek
    -0.06
     turnaround
    -0.06
    LOWER
    -0.06
     Cous
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    _release
    0.06
     prohibiting
    0.06
     önemlidir
    0.06
    лив
    0.06
    搭
    0.06
    bast
    0.06
    .TextEdit
    0.05
     lure
    0.05
    .less
    0.05
    .VK
    0.05
    Act Density 0.054%

    No Known Activations