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

    Neuronpedia

    INDEX
    Explanations

    Questions/Chinese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Safe
    -0.07
    Misc
    -0.07
     нем
    -0.06
     PVC
    -0.06
    Failure
    -0.06
    arrant
    -0.06
     NPCs
    -0.06
     <![
    -0.06
     Pony
    -0.06
    aside
    -0.06
    POSITIVE LOGITS
    问
    0.08
     PTR
    0.07
    .BackgroundColor
    0.06
    .dataSource
    0.06
     라이
    0.06
     bergen
    0.06
     Lori
    0.06
    /trunk
    0.06
    ++;
    0.06
     UNIVERSITY
    0.06
    Act Density 0.003%

    No Known Activations