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

    Neuronpedia

    INDEX
    Explanations

    domain-specific vocabulary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tento
    0.62
     druge
    0.56
     acest
    0.48
     Tento
    0.48
     logam
    0.47
     titik
    0.47
     quente
    0.46
     narzęd
    0.46
     indie
    0.45
     innych
    0.45
    POSITIVE LOGITS
    也
    0.62
    ，
    0.60
    可以
    0.57
    不
    0.55
    就
    0.53
    有
    0.53
    出
    0.51
    更是
    0.49
    已经
    0.48
    亦
    0.48
    Act Density 0.010%

    No Known Activations