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

    Neuronpedia

    INDEX
    Explanations

    instruction beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    跟我
    0.39
    帮忙
    0.38
    ">,</
    0.38
     amén
    0.37
     minute
    0.36
     shap
    0.35
     overhaul
    0.35
    生成的
    0.35
    和我
    0.35
     finely
    0.34
    POSITIVE LOGITS
     guna
    0.35
    Rt
    0.35
    常用的
    0.35
    Meteor
    0.34
     최고
    0.33
    IKA
    0.33
    य
    0.33
    積極的に
    0.33
     زیرا
    0.33
    elis
    0.33
    Act Density 0.000%

    No Known Activations