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

    Neuronpedia

    INDEX
    Explanations

    freedom and liberty across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    x
    1.24
    v
    1.23
    p
    1.06
    1
    1.05
    w
    1.04
    c
    1.02
    l
    1.00
    u
    0.89
    y
    0.89
    म
    0.88
    POSITIVE LOGITS
     libertà
    1.37
     freedom
    1.33
     liberté
    1.24
     Freiheit
    1.20
     Freedom
    1.15
     liberty
    1.13
    freedom
    1.08
     liberdade
    1.08
     freedoms
    1.03
     libertad
    1.02
    Act Density 0.043%

    No Known Activations