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

    Neuronpedia

    INDEX
    Explanations

    using ... A

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ÑĶ
    -0.09
     gol
    -0.08
     contempor
    -0.08
     trop
    -0.08
     monkey
    -0.08
     Prototype
    -0.08
     Arcade
    -0.08
    ie
    -0.08
    ainted
    -0.07
     vir
    -0.07
    POSITIVE LOGITS
     etc
    0.15
    etc
    0.15
    .tie
    0.09
     )\n\n\n\n\n\n\n\n
    0.09
    ëĵ±
    0.09
    VertexArray
    0.09
    ̣
    0.09
    oader
    0.08
    /xhtml
    0.08
    apes
    0.08
    Act Density 0.173%

    No Known Activations