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

    Neuronpedia

    INDEX
    Explanations

    starting the day's activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಊ
    0.40
     dreadful
    0.39
    三天
    0.39
    ্ঞ
    0.38
     Caesars
    0.38
    ೋಜನ
    0.37
     misery
    0.37
     seashells
    0.37
     ANYTHING
    0.36
    пей
    0.36
    POSITIVE LOGITS
     zunächst
    0.49
     først
    0.45
     begin
    0.44
     moved
    0.43
     przen
    0.43
    থমে
    0.43
     먼저
    0.41
     first
    0.40
     primero
    0.40
    首先
    0.40
    Act Density 0.023%

    No Known Activations