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

    Neuronpedia

    INDEX
    Explanations

    guiding actions gently and repeatedly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     അത്
    0.39
     शॉर्ट
    0.38
    一下子
    0.37
     അഭിപ്
    0.37
     misfortune
    0.37
     proporcion
    0.36
     misfort
    0.36
     motorcycl
    0.36
     amphibious
    0.36
     thoughtfulness
    0.36
    POSITIVE LOGITS
     όταν
    0.49
     continuamente
    0.48
     whenever
    0.46
     लगातार
    0.45
    เมื่อ
    0.44
    بعد
    0.44
     cuando
    0.43
     بعد
    0.43
    いつでも
    0.43
     continually
    0.43
    Act Density 0.013%

    No Known Activations