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

    Neuronpedia

    INDEX
    Explanations

    BLOCK

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ニニ
    -0.07
    ẹp
    -0.07
     ż
    -0.07
     Funeral
    -0.06
    ектив
    -0.06
    803
    -0.06
    emonic
    -0.06
    ισμός
    -0.06
     Tomb
    -0.06
     nối
    -0.06
    POSITIVE LOGITS
     yielding
    0.07
    outside
    0.07
     Wayne
    0.06
     victims
    0.06
     familia
    0.06
     experience
    0.06
     prevented
    0.06
     Evolution
    0.06
     beginning
    0.06
     universe
    0.06
    Act Density 0.001%

    No Known Activations