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

    Neuronpedia

    INDEX
    Explanations

    by the time or century

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     প্রথমে
    0.56
     ആദ്യം
    0.52
     firstly
    0.51
     zunächst
    0.51
     zuerst
    0.48
     contrairement
    0.48
    賖
    0.47
     ինչ
    0.46
     recentemente
    0.46
     সংরক্ষণ
    0.46
    POSITIVE LOGITS
     already
    0.75
     ormai
    0.72
     fully
    0.71
     چکے
    0.70
    middels
    0.70
     כבר
    0.68
     sudah
    0.65
    既に
    0.65
     Already
    0.65
    已经
    0.64
    Act Density 0.046%

    No Known Activations