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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    operators
    -0.07
     ['/
    -0.06
     nextProps
    -0.06
    �p
    -0.06
     výstav
    -0.06
     onTap
    -0.06
    stacle
    -0.06
     infringement
    -0.06
    Employee
    -0.06
    undred
    -0.06
    POSITIVE LOGITS
    ↵↵↵
    0.07
     websites
    0.07
    erk
    0.06
    Euro
    0.06
     siyas
    0.06
     URL
    0.06
    .Basic
    0.06
    редел
    0.06
    LR
    0.06
     miễn
    0.06
    Act Density 0.029%

    No Known Activations