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

    Neuronpedia

    INDEX
    Explanations

    expected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     employed
    -0.08
     Fred
    -0.07
     inspectors
    -0.07
     услуг
    -0.07
    났
    -0.06
     прох
    -0.06
     overflowing
    -0.06
     رود
    -0.06
    ाब
    -0.06
    acement
    -0.06
    POSITIVE LOGITS
     Julie
    0.07
    "){
↵
    0.06
    靈
    0.06
    (argv
    0.06
    Dom
    0.06
    [type
    0.06
     Gang
    0.06
     gn
    0.06
    :null
    0.06
     perpetrated
    0.06
    Act Density 0.019%

    No Known Activations