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

    Neuronpedia

    INDEX
    Explanations

    Experiencing something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    似的
    -0.07
    iptables
    -0.06
    CD
    -0.06
    孩子
    -0.06
     ↵	↵
    -0.06
     нос
    -0.06
    -*-
    -0.06
    matic
    -0.06
     части
    -0.06
    Short
    -0.06
    POSITIVE LOGITS
    rière
    0.06
     Military
    0.06
     confront
    0.06
     bullied
    0.06
     CIF
    0.06
     threw
    0.06
    .pat
    0.06
     cerr
    0.06
     wardrobe
    0.06
     Cult
    0.06
    Act Density 0.253%

    No Known Activations