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

    Neuronpedia

    INDEX
    Explanations

    llama model fine-tuning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    山
    0.45
    체의
    0.44
    Ｌ
    0.43
     Definitions
    0.43
    广告
    0.43
    ，
    0.43
    风
    0.42
    廣告
    0.42
    去
    0.42
     일
    0.42
    POSITIVE LOGITS
     sosyal
    0.52
    veyard
    0.48
     unjustly
    0.48
    relation
    0.46
     defended
    0.45
     आधारित
    0.44
    sortTable
    0.44
     memakai
    0.44
     occasion
    0.43
    DISCUSSION
    0.42
    Act Density 0.001%

    No Known Activations