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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rant
    -0.07
     estimating
    -0.07
    	O
    -0.06
     imposition
    -0.06
     hospitalized
    -0.06
     Uma
    -0.06
    -Based
    -0.06
     �
    -0.06
     domic
    -0.06
     مو
    -0.06
    POSITIVE LOGITS
     THROUGH
    0.08
     through
    0.07
    _clean
    0.07
     transportation
    0.07
    UIView
    0.07
    VALID
    0.07
     slideshow
    0.07
     �
    0.07
    through
    0.07
    .wind
    0.07
    Act Density 0.019%

    No Known Activations