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

    Neuronpedia

    INDEX
    Explanations

    groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Business
    -0.07
     data
    -0.07
     quest
    -0.07
    ukan
    -0.07
     Economic
    -0.07
     سف
    -0.06
     Security
    -0.06
     Washington
    -0.06
     tế
    -0.06
    ICAST
    -0.06
    POSITIVE LOGITS
    Pří
    0.07
    ㅠ
    0.06
    !");
    0.06
    Δεν
    0.06
    .did
    0.06
    .getLeft
    0.06
     inaccessible
    0.06
     strips
    0.06
     вкус
    0.06
    ,in
    0.06
    Act Density 0.182%

    No Known Activations