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

    Neuronpedia

    INDEX
    Explanations

    universalization, strategy tester

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Thoreau
    0.42
     '{
    0.42
    رد
    0.41
     seguire
    0.40
    林的
    0.39
     😉
    0.37
    生成的
    0.37
     '+
    0.36
    𒉡
    0.36
     geben
    0.36
    POSITIVE LOGITS
    編集
    0.43
     Bhos
    0.40
    вит
    0.37
     मंदिर
    0.37
     మూ
    0.36
    iles
    0.36
    વે
    0.36
    ◥
    0.36
    тини
    0.35
     Anonymous
    0.35
    Act Density 0.000%

    No Known Activations