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

    Neuronpedia

    INDEX
    Explanations

    commas and "and"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     정부
    -0.07
    ';
↵
↵
    -0.07
    itin
    -0.06
     Seats
    -0.06
     Boxes
    -0.06
     DefaultValue
    -0.06
    诉
    -0.06
    kart
    -0.06
    surface
    -0.06
    .(
    -0.06
    POSITIVE LOGITS
    Fetching
    0.07
    .Question
    0.07
    mp
    0.07
    .borrow
    0.06
    ağ
    0.06
     pam
    0.06
    =$((
    0.06
    emás
    0.06
    　 　 　 　 　 　
    0.06
     ubuntu
    0.06
    Act Density 0.017%

    No Known Activations