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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hess
    -0.07
     chewing
    -0.07
     كما
    -0.07
    Byte
    -0.07
     任
    -0.06
     draggable
    -0.06
    RoleId
    -0.06
    �
    -0.06
     võ
    -0.06
    順
    -0.06
    POSITIVE LOGITS
    "]){↵
    0.07
     buen
    0.07
    (emp
    0.07
     kostenlose
    0.06
     вихов
    0.06
    barcode
    0.06
    λλι
    0.06
    $b
    0.06
    sterdam
    0.06
    (target
    0.06
    Act Density 0.004%

    No Known Activations