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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Perez
    -0.08
    -0.08
    -guid
    -0.08
     используется
    -0.08
     Jacobs
    -0.08
    ículo
    -0.08
    ország
    -0.07
     대한민국
    -0.07
     ensin
    -0.07
    Horiz
    -0.07
    POSITIVE LOGITS
     wanting
    0.12
     want
    0.11
    Want
    0.10
     Want
    0.10
     muốn
    0.10
     souhaitent
    0.10
     ønsker
    0.09
     ترغب
    0.09
     хотят
    0.09
     غواړي
    0.09
    Act Density 0.073%
    No Known Activations