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

    Neuronpedia

    INDEX
    Explanations

    multilingual programming tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     this
    0.29
     of
    0.28
     context
    0.27
     {
    0.27
     phenotype
    0.27
     Health
    0.26
     namespace
    0.26
    0.26
     class
    0.25
     The
    0.25
    POSITIVE LOGITS
    Yeni
    0.35
    ೬
    0.35
     אבל
    0.34
    แมนเชสเตอร์ซิตี
    0.34
    ๖
    0.33
    }=$
    0.32
    ૭
    0.32
     ఇతర
    0.32
    ૫
    0.32
    }$;
    0.32
    Act Density 0.549%

    No Known Activations