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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unle
    -0.07
     Vũ
    -0.07
     apis
    -0.07
     Filtering
    -0.07
    IDER
    -0.07
    ार
    -0.07
    matcher
    -0.06
    젝
    -0.06
    st
    -0.06
    boot
    -0.06
    POSITIVE LOGITS
    ości
    0.07
     terribly
    0.07
    -seeking
    0.07
     oneself
    0.06
    anno
    0.06
    ονται
    0.06
    Factors
    0.06
    Towards
    0.06
    Changing
    0.06
    jected
    0.06
    Act Density 0.006%

    No Known Activations