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

    Neuronpedia

    INDEX
    Explanations

    seize control or territory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    К
    0.52
    '),
    0.51
    ');
    0.48
    ），
    0.47
    内
    0.46
    أن
    0.46
    ی
    0.45
     corros
    0.43
    '
    0.43
    `),
    0.42
    POSITIVE LOGITS
    вил
    0.48
     Таким
    0.47
     Thereafter
    0.47
    raisal
    0.45
    来越
    0.45
     গিয়াছে
    0.44
    來越
    0.44
    ö
    0.44
     Dich
    0.43
     Blot
    0.43
    Act Density 0.002%

    No Known Activations