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

    Neuronpedia

    INDEX
    Explanations

    patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wa
    -0.07
     radix
    -0.06
    .sqrt
    -0.06
    WA
    -0.06
     goodness
    -0.06
     Stanford
    -0.06
    Transformation
    -0.06
    wstring
    -0.06
    /gallery
    -0.06
    ーの
    -0.05
    POSITIVE LOGITS
     verbess
    0.08
    	resp
    0.07
     producción
    0.07
    remarks
    0.07
     onsite
    0.06
    	map
    0.06
     Proceed
    0.06
    	fill
    0.06
    imento
    0.06
     salir
    0.06
    Act Density 0.016%

    No Known Activations