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

    Neuronpedia

    INDEX
    Explanations

    best of both worlds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    up
    0.58
    小数
    0.56
    িলাম
    0.54
    billion
    0.54
    htë
    0.52
    litre
    0.52
    ups
    0.52
    2
    0.51
    asin
    0.50
    figures
    0.50
    POSITIVE LOGITS
     требо
    0.47
    琇
    0.47
     Gemeinde
    0.46
    Université
    0.46
     revitalization
    0.46
    吿
    0.46
     свобод
    0.46
    Después
    0.46
     παρέ
    0.46
     проблемы
    0.45
    Act Density 0.000%

    No Known Activations