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

    Neuronpedia

    INDEX
    Explanations

    Liberty (places or things)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    Cum
    -0.07
    通知
    -0.07
    Actual
    -0.07
    ğitim
    -0.07
    —an
    -0.07
     kém
    -0.07
     en
    -0.07
    オン
    -0.07
     Cohen
    -0.07
    POSITIVE LOGITS
     Liberty
    0.18
     liberty
    0.13
     liberties
    0.11
     libert
    0.08
     Libre
    0.08
     Liberties
    0.07
     Libert
    0.07
     libero
    0.07
     ty
    0.07
     Pirates
    0.07
    Act Density 0.004%

    No Known Activations