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

    Neuronpedia

    INDEX
    Explanations

    visual modes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CHANGE
    0.47
     호출
    0.46
    Narrow
    0.46
     スリム
    0.46
    ট
    0.46
    FTWARE
    0.45
     membri
    0.45
    Focused
    0.45
    Voids
    0.43
     сотрудников
    0.43
    POSITIVE LOGITS
     now
    0.54
    ки
    0.50
     on
    0.45
    iteit
    0.45
     hadn
    0.44
    an
    0.44
     can
    0.44
    𝗮
    0.43
     Mac
    0.43
    ithub
    0.42
    Act Density 0.001%

    No Known Activations