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

    Neuronpedia

    INDEX
    Explanations

    kilograms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     சரும
    0.44
     новым
    0.44
     设备
    0.44
    стема
    0.43
     اصحاب
    0.42
     获取
    0.41
     akses
    0.41
     alimento
    0.41
    صحاب
    0.40
     проблема
    0.40
    POSITIVE LOGITS
    nia
    0.42
    ื่อย
    0.41
    ہ
    0.39
    ust
    0.38
    ia
    0.38
     slash
    0.38
     synt
    0.38
    ovis
    0.38
     ning
    0.37
    Nature
    0.37
    Act Density 0.002%

    No Known Activations