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

    Neuronpedia

    INDEX
    Explanations

    sterile, professional, infringing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Еў
    0.50
     wifi
    0.49
     JVM
    0.46
     Вол
    0.46
     게
    0.45
     Ballot
    0.45
    िफ्ट
    0.45
    ोग्रा
    0.44
     velcro
    0.44
     Marines
    0.44
    POSITIVE LOGITS
    -
    0.57
    /
    0.54
    ção
    0.47
    潭
    0.46
    Research
    0.46
    러스
    0.45
     tersebut
    0.43
    ress
    0.42
    were
    0.42
    Tutorial
    0.42
    Act Density 0.001%

    No Known Activations