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

    Neuronpedia

    INDEX
    Explanations

    modelCapital Contributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    krét
    0.49
     प्रकल्प
    0.48
     हेमंत
    0.47
    лм
    0.47
    លេ
    0.47
    VisualStyle
    0.47
     Стаўкі
    0.47
    zzel
    0.46
    ckiej
    0.46
     IntVar
    0.46
    POSITIVE LOGITS
     toga
    0.53
    ın
    0.51
     coconut
    0.48
     margarine
    0.47
     نتیجه
    0.47
     y
    0.46
     croire
    0.46
    ון
    0.46
    の
    0.46
     ¬
    0.46
    Act Density 0.000%

    No Known Activations