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

    Neuronpedia

    INDEX
    Explanations

    hal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -break
    -0.07
    acement
    -0.07
    ecimal
    -0.07
     steadily
    -0.06
    idual
    -0.06
    uento
    -0.06
     crack
    -0.06
    Bottom
    -0.06
     Injector
    -0.06
     Modify
    -0.06
    POSITIVE LOGITS
     )↵↵↵
    0.07
     Hospitality
    0.07
    ♪↵↵
    0.07
     Plzeň
    0.06
    ()])↵
    0.06
     हट
    0.06
     disposable
    0.06
     Pipeline
    0.06
    ↵↵↵
    0.06
     أمريكي
    0.06
    Act Density 0.002%

    No Known Activations