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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gi
    -0.07
     зд
    -0.07
     Canter
    -0.07
     reveal
    -0.06
     causal
    -0.06
    odial
    -0.06
    ्रदर
    -0.06
    Result
    -0.06
    Arc
    -0.06
    빌
    -0.06
    POSITIVE LOGITS
    из
    0.07
     از
    0.07
    ="{{$
    0.06
    .rdf
    0.06
     Profile
    0.06
    (TestCase
    0.06
     společnost
    0.06
    ção
    0.06
    akan
    0.06
     Armen
    0.06
    Act Density 0.000%

    No Known Activations