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

    Neuronpedia

    INDEX
    Explanations

    arms control limitation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mischung
    -0.09
     빠
    -0.08
    �
    -0.08
     내부
    -0.08
     hazır
    -0.08
    طان
    -0.08
    料理
    -0.08
    .localized
    -0.08
     العالية
    -0.08
     chứa
    -0.08
    POSITIVE LOGITS
    减少
    0.10
     restrict
    0.10
     vow
    0.09
    Limits
    0.09
     കുറ
    0.09
     Limits
    0.09
     treaty
    0.08
     limits
    0.08
     vows
    0.08
     reductions
    0.08
    Act Density 0.008%

    No Known Activations