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

    Neuronpedia

    INDEX
    Explanations

    parentheses and quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Networking
    -0.07
    ेयर
    -0.06
    획
    -0.06
     Injectable
    -0.06
    din
    -0.06
    _PASSWORD
    -0.06
     HashSet
    -0.06
    (grad
    -0.06
    SimpleName
    -0.06
    Kel
    -0.06
    POSITIVE LOGITS
    anship
    0.07
     ={↵
    0.06
    .Take
    0.06
    graded
    0.06
     literal
    0.06
    �
    0.06
     suburbs
    0.06
    >');↵
    0.06
     LIMIT
    0.06
    工具
    0.06
    Act Density 0.026%

    No Known Activations