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

    Neuronpedia

    INDEX
    Explanations

    offset

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ímetros
    -0.07
     �
    -0.07
    教
    -0.07
    产生
    -0.07
    扩
    -0.07
    知道
    -0.07
    指标
    -0.07
     deserialize
    -0.07
    ిచ
    -0.07
    metrics
    -0.07
    POSITIVE LOGITS
     stagger
    0.10
     solidaridad
    0.10
    _OFFSET
    0.10
     ώστε
    0.10
     Opposition
    0.10
     જેથી
    0.10
    -offset
    0.09
     соль
    0.09
     opposition
    0.09
     যাতে
    0.09
    Act Density 0.008%

    No Known Activations