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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     búsqueda
    -0.06
     onResume
    -0.06
     diesen
    -0.06
    ANN
    -0.06
     مو
    -0.06
    	Use
    -0.06
     tensor
    -0.06
     myst
    -0.06
    /usr
    -0.06
    .support
    -0.06
    POSITIVE LOGITS
    Length
    0.07
     rode
    0.07
     inmate
    0.07
     Shipping
    0.06
    FormControl
    0.06
    lyph
    0.06
    entimes
    0.06
    urities
    0.06
    igans
    0.06
     kra
    0.06
    Act Density 0.056%

    No Known Activations