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

    Neuronpedia

    INDEX
    Explanations

    Encouraging help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Learn
    0.44
    ᡵ
    0.44
    learn
    0.43
     දැ
    0.43
    Insights
    0.40
     jums
    0.39
    当你
    0.39
     encontrarás
    0.39
    あなたは
    0.39
     Learn
    0.38
    POSITIVE LOGITS
     encourage
    1.62
     Encourage
    1.61
    鼓励
    1.52
    鼓勵
    1.46
     encouraging
    1.44
    encour
    1.34
     encourages
    1.28
     Encour
    1.28
     encouragement
    1.23
     encouraged
    1.22
    Act Density 0.018%

    No Known Activations