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

    Neuronpedia

    INDEX
    Explanations

    tongue twisters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ShouldBe
    -0.07
    Authority
    -0.06
    det
    -0.06
     urč
    -0.06
     slow
    -0.06
     Studi
    -0.06
    ADA
    -0.06
    �
    -0.06
    аду
    -0.06
    .getStart
    -0.06
    POSITIVE LOGITS
    )throws
    0.08
    .Handler
    0.07
     Cath
    0.07
                                   ↵
    0.07
     XMLHttpRequest
    0.07
     upbeat
    0.06
     outright
    0.06
     üzerindeki
    0.06
    -reader
    0.06
    ’en
    0.06
    Act Density 0.001%

    No Known Activations