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

    Neuronpedia

    INDEX
    Explanations

    Negativity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     region
    -1.34
     región
    -0.99
    region
    -0.95
     Region
    -0.91
     lack
    -0.90
     regione
    -0.84
     região
    -0.81
     REGION
    -0.81
     région
    -0.80
    Region
    -0.78
    POSITIVE LOGITS
     of
    0.92
    able
    0.82
    sidemargin
    0.68
    ed
    0.67
    ings
    0.66
    alised
    0.64
    ality
    0.62
    ers
    0.61
     Athenians
    0.61
    ful
    0.59
    Act Density 0.044%

    No Known Activations