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

    Neuronpedia

    INDEX
    Explanations

    can find more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imod
    0.40
     গুপ্ত
    0.39
     பேச
    0.38
    を取得
    0.38
     世
    0.38
     amort
    0.37
     interpreta
    0.37
    稒
    0.37
     trening
    0.37
     interpretar
    0.37
    POSITIVE LOGITS
     delve
    0.90
     delves
    0.79
     further
    0.77
     dive
    0.77
     explore
    0.77
    Further
    0.76
    Explore
    0.75
     مزید
    0.74
     dives
    0.74
     узнать
    0.73
    Act Density 0.025%

    No Known Activations