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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    突破
    -0.08
     begele
    -0.08
     begeleiding
    -0.08
     třeba
    -0.07
     breakthroughs
    -0.07
    持续
    -0.07
     breakthrough
    -0.07
    长龙
    -0.07
    lasting
    -0.07
    iation
    -0.07
    POSITIVE LOGITS
    Same
    0.09
     skat
    0.09
     वही
    0.09
    Replace
    0.09
    ICP备
    0.08
     recom
    0.08
     mirrored
    0.08
    Compare
    0.08
    Mirror
    0.08
    пони
    0.08
    Act Density 0.060%

    No Known Activations