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

    Neuronpedia

    INDEX
    Explanations

    city names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dest
    -0.08
     وفي
    -0.07
     й
    -0.07
     Buk
    -0.07
     раск
    -0.07
     tvrd
    -0.07
     targ
    -0.07
    emand
    -0.07
    CCCCCC
    -0.06
    igmoid
    -0.06
    POSITIVE LOGITS
     congressional
    0.07
    012
    0.06
    VertexAttribArray
    0.06
     espan
    0.06
    НИ
    0.06
    ียด
    0.06
     Institution
    0.06
    Throws
    0.06
     İstanbul
    0.06
    اهش
    0.06
    Act Density 0.066%

    No Known Activations