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

    Neuronpedia

    INDEX
    Explanations

    Code snippet field extraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peers
    -0.08
     নির্দেশ
    -0.07
     peer
    -0.07
     houver
    -0.07
    .peer
    -0.07
    -0.07
     infusion
    -0.07
     существуют
    -0.07
    环球
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     selective
    0.11
     extracting
    0.10
     extraction
    0.10
     subset
    0.10
     pertinent
    0.10
     geïnteresseerd
    0.10
    Selective
    0.10
     Extract
    0.09
     pertinentes
    0.09
    Extract
    0.09
    Act Density 0.019%
    No Known Activations