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

    Neuronpedia

    INDEX
    Explanations

    largest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coloring
    -0.07
     очи
    -0.06
    iliki
    -0.06
    .='<
    -0.06
     Rahul
    -0.06
    ).^
    -0.06
     Walk
    -0.06
     mostr
    -0.06
    -ब
    -0.06
    /the
    -0.05
    POSITIVE LOGITS
     resale
    0.07
     dw
    0.07
     Sql
    0.07
    Ver
    0.07
    	Matrix
    0.07
    }?
    0.07
    engkap
    0.07
    _hr
    0.07
    iz
    0.07
     eru
    0.07
    Act Density 0.000%

    No Known Activations