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

    Neuronpedia

    INDEX
    Explanations

    understand you might

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yourselves
    0.50
     yourself
    0.48
     usted
    0.44
    你也
    0.41
    您的
    0.40
     rightfully
    0.40
    cccs
    0.40
     نفسه
    0.39
     knows
    0.38
     understands
    0.38
    POSITIVE LOGITS
     レン
    0.40
    给人
    0.38
     מד
    0.38
     smrt
    0.37
    吏
    0.37
    bankruptcy
    0.36
    ispielsweise
    0.36
    侨
    0.36
     TIT
    0.36
     ide
    0.35
    Act Density 0.002%

    No Known Activations