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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \modules
    -0.08
    ↵
    -0.07
    cü
    -0.07
    Fmt
    -0.07
     
↵
    -0.07
    งใน
    -0.06
    _PRINTF
    -0.06
    -stop
    -0.06
    bps
    -0.06
    ард
    -0.06
    POSITIVE LOGITS
    532
    0.07
    _prices
    0.07
    .ShouldBe
    0.06
    .routes
    0.06
     advisor
    0.06
    .didReceiveMemoryWarning
    0.06
     khắc
    0.06
     preocup
    0.06
    210
    0.06
     touching
    0.06
    Act Density 0.042%

    No Known Activations