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

    Neuronpedia

    INDEX
    Explanations

    Okay, here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lington
    0.70
     fountains
    0.68
     northwest
    0.67
    咾
    0.67
     configuration
    0.66
     configurations
    0.66
     Shui
    0.65
     होम्योपै
    0.65
    !',
    0.64
    sthresh
    0.64
    POSITIVE LOGITS
     here
    0.75
     Here
    0.70
     здесь
    0.70
    Here
    0.65
     এখানে
    0.65
     ویس
    0.65
    ここに
    0.64
     сюда
    0.64
    here
    0.63
     HERE
    0.63
    Act Density 0.137%

    No Known Activations