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

    Neuronpedia

    INDEX
    Explanations

    still or remains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kolei
    0.69
    ISIONS
    0.69
    긋
    0.69
     लीजिए
    0.68
     みたい
    0.67
    <ul>
    0.67
    მარ
    0.65
    देवी
    0.65
     Erweiter
    0.65
    יוחד
    0.65
    POSITIVE LOGITS
     still
    6.37
    still
    5.51
     Still
    5.50
    Still
    5.36
     STILL
    4.99
    仍然
    4.80
    仍
    4.50
     masih
    4.47
     vẫn
    4.45
     fortfarande
    4.35
    Act Density 0.649%

    No Known Activations