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

    Neuronpedia

    INDEX
    Explanations

    falling and plunging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dilate
    0.81
     Vaccination
    0.78
    熏
    0.77
     क्रेडिट
    0.76
     मीरा
    0.75
     tokenizer
    0.74
     вакци
    0.74
     Tensor
    0.73
     vaccine
    0.73
     vaccinated
    0.73
    POSITIVE LOGITS
     plummet
    1.63
     سقوط
    1.44
     descent
    1.43
     fall
    1.42
    坠
    1.39
     falls
    1.37
     parachute
    1.37
    Falls
    1.35
    落下
    1.35
     drop
    1.33
    Act Density 0.162%

    No Known Activations